video platform engineers

Abstract: Video understanding keeps moving toward longer recordings, and the longer a recording is, the more questions can be asked about it. But processing it again for every question does not scale, so many systems watch the video once, build a memory, and answer later questions from it. Yet what to remember is decided before anyone knows what will be asked, and whatever is left out cannot be recovered later. Moreover, whether the savings pay off is judged by token counts, which fall when the input gets shorter but not when the model reuses what it has already computed. We present REEL, an evaluation framework that compares three saved representations built from exactly the same observed frames, so that a change in answers can come only from what the system remembered. Text writes a short record of what happened, Visual keeps the encoder outputs, and Prefix State also keeps the language-model prefix. Each is compared with full reprocessing (Frames) by paired correctness changes, cumulative GPU time, and storage size. Across six vision-language models and two benchmarks, Text and Frames differ in correctness on 20\% to 29\% of questions, even when their mean accuracy is almost the same. By contrast, Visual and Prefix State stay much closer to Frames. With unlimited storage, Prefix State is the cheapest in total GPU time among memories that keep almost all of the answers Frames gets right, for every model on both benchmarks. The trade-off is storage: Prefix State keeps up to about 21 GiB per video, whereas Text needs only kilobytes. Reusing computation and discarding information both look like efficiency, but only the second removes evidence that later questions may need, and neither mean accuracy nor token count tells them apart. REEL makes that difference measurable for any system that answers many questions from one saved memory.

Abstract: Engagement-optimized content recommendation systems exhibit a well-documented rich-get-richer dynamic that structurally disadvantages emerging creators on large-scale platforms. Evaluating debiasing interventions at scale demands faithful simulation of creator-viewer ecosystems, yet the fidelity, diversity, and validity of such simulators remain underexplored. We present a grounded user-simulation framework that models a heterogeneous population of ${\sim}42$K creators and their coupled viewer interactions over 12~weeks, and use it to evaluate equitable view-allocation policies formulated as a budgeted multi-armed bandit (MAB). The simulator captures three behavioral dimensions: (i)~\textbf{creator diversity}, modeled via a clustering approach grounded in real platform creator-level distributions; (ii)~\textbf{behavioral fidelity}, captured through coupled creator-content state machines that represent growth trajectories, engagement accumulation, and graduation dynamics; and (iii)~\textbf{population-level validity}, measured by calibration against observed platform metrics. We evaluate simulative-configurations that vary content-viewership target definitions, reward functions, and a small-creator reserve lever to maximize creator-content recommendation equity. A floor-protected per content-view-target with a view-parity-gap reward guarantees 90\% of view targets being met by creators every week, grows small-creator organic reach ${\sim}{+}33\%$ per week, and achieves high distribution stability (set of creators with funded-views Jaccard $= 0.819$). We analyze the Sim2Real gap and propose validation protocols, contributing evidence for when simulation-derived fairness conclusions can be trusted.

Abstract: End-to-end video quality assessment (VQA) methods leave the regional evidence underlying their predictions largely implicit. We introduce an explicit pixel-level regional representation for VQA, instantiated as a Quality-Relevance Heatmap (QRH) that combines localized degradation evidence with perceptual priors under vision-language model guidance, without requiring pixel-level annotations. We apply QRH to existing VQA models through two deterministic fragment-sampling strategies: distribution-preserving sampling approximates the original sampler's QRH-score distribution without retraining, while quality-aware sampling prioritizes regions with high QRH scores and is paired with fine-tuning. Experiments with DOVER on multiple benchmarks show that the former closely approximates predictions averaged over random samples, while the latter improves most evaluated metrics across popular VQA benchmarks. These results support explicit regional representations as a useful interface for downstream VQA.

Abstract: Real-time streaming video question answering with vision-language models must answer queries that arrive at any time with low latency while sustaining the video-processing rate required by the application. Existing systems construct key-value (KV) caches for the entire video as it arrives, although a query typically uses only a few of the preceding frames as evidence. This highlights a fundamental trade-off: performing more computation as video arrives reduces query-time computation but can increase processing lag, whereas deferring computation can increase the video-processing rate but requires additional query-time computation for retrieved content. We present StreamAhead, an algorithm-system co-design that exploits this trade-off through adaptive precomputation: dynamically controlling how much computation to complete for each video segment before a query arrives. StreamAhead encodes video segments independently and lets each remain at a different representation level, from inexpensive visual features to costly KV caches, completing KV caches only for the retrieved segments when a query arrives. StreamAhead profiles offline the cost of advancing a segment to each representation level. Its runtime uses these profiles to schedule segment computation concurrently with query execution, pipelining it across heterogeneous CPU and GPU resources while maintaining the required video-processing rate. StreamAhead achieves accuracy competitive with state-of-the-art methods with up to 10.4x lower time-to-first-token (TTFT), and up to 5.9x lower TTFT than state-of-the-art streaming systems. It sustains 30 FPS with P95 TTFT under 0.5 s, and up to 57 FPS with P95 TTFT under 2 s. To our knowledge, StreamAhead is the first real-time streaming video QA system with competitive accuracy, setting a new Pareto frontier between video-processing rate and TTFT.

Abstract: Multimodal Large Language Models (MLLMs) face significant scalability challenges in long-video understanding due to quadratic attention complexity and context window constraints. Existing retrieval-based approaches typically rely on supervised learning from static keyframe annotations. However, these label priors often fail to align with the actual information required by downstream MLLMs for complex reasoning, creating a misalignment between the training target and inference needs. To bridge this gap, we propose a probabilistic framework that reformulates frame selection as latent-variable inference. We first initialize a lightweight policy using supervised learning to capture general visual saliency. Then, we treat a frozen MLLM as a task environment and use its answer likelihood as dense task evidence to refine the policy via Bayesian Group Relative Policy Optimization (GRPO). Within this formulation, the negative log-likelihood (NLL) over ground-truth answer tokens provides a principled dense reward, while a prior-matching KL term preserves semantic consistency with the elicited label prior. This process transitions the selection principle from static label priors to task evidence. Extensive experiments on Video-MME, MLVU, and LongVideoBench demonstrate that our selector achieves competitive accuracy with MLLM-based scorers while retaining the inference efficiency of lightweight methods. The selector is trained once with a frozen MLLM environment and transfers directly to multiple downstream MLLMs without retraining. Code is available at \url{github.com/Miraclecsc/Frame_Selection_GRPO}.

Abstract: Comparing videos to assess their semantic similarity remains a challenging task for current Large Multimodal Models (LMMs), which are primarily trained with single-video objectives. While most prior works have focused on computing global similarity, recent studies have introduced the more challenging problem of concept-based similarity, which measures how similar two videos are with respect to specific concepts (e.g., activity, location). However, no dedicated approaches have yet leveraged LMMs to explicitly address this task. In this paper, we aim to fill this gap introducing Video Caption Entailment for video similarity estimation (VICE): a dual-branch design that leverages LMMs for cross-video reasoning. Each branch jointly processes one video and the caption of the other, measuring their alignment for a specific concept via video-language entailment. The outputs from both branches are fused to produce a final similarity score, along with a textual explanation of the model reasoning. This approach leverages the model's native single-video understanding while enabling fine-grained comparative reasoning between video and text. Experiments on ConViS-Bench and StepDiff show that VICE outperforms models that process both videos simultaneously, highlighting the promise of single-video reasoning for concept-based similarity estimation.

Abstract: Diffusion Transformers (DiTs) dominate video generation but suffer from high inference cost due to the quadratic complexity of self-attention. Sparse attention mitigates this by skipping unnecessary computation in the attention matrix, but existing methods apply a fixed sparsity ratio throughout denoising and struggle to accurately determine which computations to skip. To address these limitations, we analyze attention dynamics through attention entropy and mean attention distance, and find that attention becomes increasingly concentrated across denoising steps. We further observe that blocks selected early continue to capture a large fraction of the total attention weight at later steps. These findings suggest two acceleration opportunities: the sparsity ratio should grow as denoising progresses, and earlier search results can be reused to reduce the search space. Based on these findings, we propose Growing Sparsity and Reduced Search (GSRS), a training-free framework that retains more computation early and progressively reduces it later, while restricting subsequent searches to an early candidate set to reduce search overhead. GSRS adopts Top-p selection for adaptive sparsity control, supported by a precise evaluation scheme that computes exact attention weights within the FlashAttention computation at negligible overhead. Experiments on HunyuanVideo and Wan 2.1 validate that GSRS achieves 1.55$\times$--2.21$\times$ speedup while maintaining generation quality comparable to full attention.

Abstract: Unsupervised temporal action localization (UTAL) aims to identify action categories and localize their temporal boundaries without annotation supervision. Existing methods typically derive supervision for both tasks solely from RGB and optical-flow representations, often resulting in noisy category assignments and inaccurate temporal boundaries. In this work, we reveal an overlooked property of video codecs: group-of-pictures quantization patterns preserve category-discriminative dynamics, while motion-vector and residual variations exhibit pronounced responses around action transitions. Based on this insight, we propose CoDy, a codec dynamics-guided framework that exploits the codec as complementary information to the visual view for UTAL. CoDy integrates a codec-enhanced view with RGB and flow through confidence-aware consensus clustering, producing reliable soft pseudo-labels. It further converts codec dynamics into a class-agnostic boundary prior, which supervises visual boundary learning and guides proposal initialization and iterative refinement. The codec branches are only used during the training stage and introduce no extra codec-side computation at inference. Extensive experiments on THUMOS14 and ActivityNet v1.3 demonstrate that CoDy consistently outperforms existing UTAL methods and achieves state-of-the-art localization performance. These results establish codec signals as effective annotation-free priors for jointly inferring which actions occur and when they occur.

Abstract: Finding the right video often requires distinguishing similar scenes in which different events occur. Joint matching improves retrieval, but processing rich video representations for each query is costly. VEDJE compresses features within sampled frames while keeping their representations separate in a reusable cache. Feature-change prediction supplies an auxiliary training signal that improves retrieval from the compressed cache without adding work at query time. On MSR-VTT, MSVD, DiDeMo, and ActivityNet, VEDJE improves R@1 over matched first-stage retrievers in both retrieval directions. On MSR-VTT, it reaches 59.8 text-to-video R@1 with a fine-tuned VideoCLIP-XL first stage. In the VideoPrism configuration, shrinking the per-video cache fourfold to 12 KiB preserves text-to-video recall within 0.2 points. These results show that accurate video search can operate on compact evidence, encoded once and reused as new queries arrive.

Abstract: Highly compressed video autoencoders offer an effective way to accelerate video diffusion models, as the Diffusion Transformer (DiT) operates on far fewer tokens. However, such autoencoders are challenging to train, since a higher compression ratio degrades reconstruction quality and recovering it requires more channels, which is known to slow the convergence of the DiT. The compressed latent also differs from the one the DiT was trained on, so the pretrained DiT must be either retrained from scratch or adapted at considerable cost. Compressing the autoencoder the DiT was trained with appears to preserve compatibility, yet optimizing it for reconstruction alone still shifts the latent away from the distribution the DiT has learned. To address this, we propose Generation-Aware Latent Compression for Efficient Video Generation (GRACE), a two-stage framework that compresses a pretrained video autoencoder while keeping it compatible with the pretrained DiT. Specifically, we keep a frozen base latent from the pretrained encoder and learn a residual latent for the information lost under stronger compression, while aligning the compressed latent with the pretrained latent in the feature space of the frozen DiT so that the autoencoder is optimized for generation. We then adapt the DiT with lightweight fine-tuning and asymmetric denoising, where the base is denoised ahead of the residual. GRACE reduces the token count of Wan2.1-I2V-14B by 8x and its latency by 11.1x at 480x832x81, while matching the generation quality of the pretrained pipeline before compression on VBench.

Abstract: AI-generated videos are rapidly increasing in volume, duration, and resolution, creating growing demands for efficient storage and transmission. Unlike natural videos captured from the physical world, AI-generated videos are samples from a learned generative distribution, where semantic structures are critical to content consistency, while many local textures and stochastic details can be plausibly regenerated. This distinction suggests that compression should preserve semantically important spatiotemporal information rather than reconstruct every pixel of a particular generative sample. Beyond reconstruction, AI-generated videos also create a practical need for prompt-based editing, where users expect to modify generated content while preserving its original spatiotemporal semantics. Motivated by these observations, we propose a unified compression and editing framework for AI-generated videos that incorporates a frozen video generator as a reusable generative prior. Within this framework, we design three spatiotemporal semantic importance-guided techniques that respectively address what to transmit, how much to transmit, and how to use the transmitted side information. First, an innovation selection method projects the latent discrepancy using spatiotemporal semantic importance, so that the selected innovations prioritize semantic invariants over replaceable generative variations. Second, a frame-adaptive bit allocation method estimates the nonuniform semantic demands of latent frames and allocates more innovations to frames requiring stronger semantic preservation. Third, a unified reconstruction and editing method continuously adjusts the influence of the transmitted side information, enabling the same compressed representation to provide strong guidance for faithful reconstruction or serve as a flexible semantic anchor for structure-preserving prompt-driven editing.

Abstract: Efficient long-video understanding with vision-language models (VLMs) is often framed as selecting informative frames or visual tokens at a fixed native resolution. We show that per-frame resolution can instead be traded for denser temporal coverage, while front-end decoding latency depends on the size of the candidate pool rather than the final token budget. An empirical study across multiple VLMs and long-video benchmarks yields three findings: dense low-resolution sampling outperforms sparse native-resolution sampling at matched token budgets; resolution-sensitive tasks benefit from selected high-resolution frames; and front-end decoding dominates wall time for hour-long videos. Motivated by these findings, we introduce LoHi, a training-free, single-pass framework that combines a dense low-resolution video stream with sparse high-resolution image frames through the VLM's native video and image pathways. LoHi-Anchor selects high-resolution frames using codec I-frame metadata, while LoHi-SemDiv uses query relevance and visual diversity over CLIP features. Across three long-video benchmarks, LoHi improves average accuracy by 10.6 percentage points over the native-resolution baseline at a matched token budget and by 5.2 percentage points over the strongest prior efficiency method. It also reduces front-end decoding latency by up to 7x on hour-long videos. Project page: https://sixundong.com/projects/lohi

Abstract: Vision-language models face a fundamental scaling bottleneck: the number of visual tokens grows with both temporal duration and spatial resolution, making long-video understanding expensive for the vision encoder and the language model. Existing methods often compress visual tokens after dense encoding, creating a mismatch between the representation used during training and the compact interface required at deployment. We present CoVisco, a codec-native vision encoder with native token compression for unified image-video understanding. By combining codec-native input support with segmented attention, CoVisco can encode long visual inputs in a single forward pass without forming dense patch-to-patch interactions across all frames. Each temporal segment is equipped with learnable abstract tokens that learn a compact segment-level representation, while fine-grained patch tokens remain available throughout the encoder. Alternating intra-segment and abstract-communication layers preserve video-level context through the abstract-token channel. A lightweight selector further exposes either abstract tokens alone or abstract tokens augmented with a runtime-selected subset of patch tokens, yielding a compact visual interface that reduces the visual context and prefill burden of downstream MLLMs while retaining fine-grained evidence when needed. Pretrained with contrastive objectives on 565M image--text pairs and 6.4M videos, CoVisco shows competitive performance on video-oriented embedding and multimodal understanding benchmarks. In the evaluated four-segment, 64-frame setting, abstract-only inference uses only 400 visual tokens while achieving video-understanding performance close to, and on some benchmarks exceeding, OneVision-Encoder. Selected patch tokens further improve fine-grained video reasoning. Project URL: https://github.com/ernie-research/CoVisco.git

Abstract: Partially Relevant Video Retrieval (PRVR) seeks to retrieve untrim-med videos containing a moment that matches a text query, without temporal annotations. The relevant moment may last only seconds within a video spanning several minutes, creating an extremely low signal-to-noise ratio that makes PRVR more challenging than standard full-video retrieval. This task presents two intertwined challenges: (1) signal dilution, where coarse global representations blur the brief relevant signal into the dominant irrelevant surroundings;(2) curvature rigidity, where embedding all videos in the same fixed-geometry space distorts representations for videos that range from flat atomic events to deep compositional hierarchies. Existing PRVR methods have improved moment selection and cross-modal matching, but they still typically encode all videos in a single fixed-curvature retrieval space, limiting their ability to model diverse video structures. To address both challenges, we propose CurvSpec, a framework that learns content-adaptive curvature for video retrieval representations rather than imposing a fixed geometric prior. CurvSpec processes features through parallel Euclidean and hyperbolic attention layers, with independently learned curvatures assigned to the hyperbolic layers, and a content-aware fusion mechanism routes each input to its most suitable geometric regime. To further suppress signal dilution, CurvSpec represents each video with semantic centroids whose number is determined by the video's content complexity, projects them onto the learned manifold, and matches each query against its nearest centroid by geodesic distance. Experiments on ActivityNet Captions, TVR, and Charades-STA demonstrate state-of-the-art retrieval performance.

Abstract: Query-agnostic streaming video understanding requires vision-language models to continuously compress an indefinitely growing visual stream into a bounded memory before future queries are known. The performance depends critically on the memory mechanism--what observations to preserve, how to represent and consolidate them, and what information to retrieve when a query eventually arrives. Rather than designing a single memory architecture by hand, we formulate memory design as a search problem over executable memory programs. We introduce a lightweight domain-specific language that expresses memory mechanisms through structured primitives for representation, admission, retention, consolidation, budgeting, and retrieval, while enforcing causal and bounded-memory constraints. Although structured, the derived program space remains large and contains heterogeneous, conditionally dependent design choices whose effects can only be assessed via downstream execution. We therefore propose MemEvo, an LLM-driven auto-research framework that uses pretrained LLM as a semantics-aware proposal model to iteratively generate and refine candidate memory programs based on accumulated experimental feedback. At runtime, a deterministic evaluation pipeline validates and evaluates each candidate, while the underlying vision-language model remains frozen throughout discovery. We finally produce a training-free, bounded-memory mechanism. Extensive experiments on StreamingBench and OVO-Bench demonstrate strong streaming video understanding performance together with substantial context and inference efficiency.

Abstract: Video-language models are increasingly used as judges of video understanding, both for evaluating model outputs and for training reward models. Whether their judgments remain reliable when the evidence is buried in day-long videos has yet to be established. Existing benchmarks cannot answer this. Their videos are typically only a few minutes long, many answer pairs can be separated from the transcript alone, and collecting human judgments does not scale to ultra-long videos. We introduce PlaylistEval, an agentic framework that builds video-language judge benchmarks over 100-hour playlist collection without human annotation. It automatically generates questions with paired answers whose differences are controlled by causal degradation, so that every pair demands retrieval across the collection. The resulting benchmark contains 630 pairs across seven domains spanning both static and dynamic knowledge, and on a stratified subset of 152 pairs it agrees with human judgments 93.0% of the time (IAA 0.781). Evaluating 17 omnimodal and multimodal models from eight families reveals that frontier judges reach only 75.4% pairwise accuracy, while open-source judge models perform far behind. We further show that both retrieval and final judgment depend on using multiple modalities, and that judge accuracy degrades as the playlist set grows. We release our pipeline, benchmark, and evaluation code at https://playlisteval.github.io.

Abstract: Recommender systems rely heavily on heterogeneous behavioral feedback to infer user preference. Although abundant, these signals are imperfect measurements: the same observed behavior can arise from different underlying states, such as genuine enjoyment, passive consumption, or inattention. The challenge is especially acute in short-form video, where watch-based signals are strongly affected by measurement confounders such as video duration - the same watch time can imply different levels of preference for videos of different lengths, while ratio-based metrics can systematically favor short videos. As a result, optimizing raw engagement can amplify measurement artifacts rather than improving user value. We propose a Factorized Latent Value Model (FLVM) for measuring user preference from heterogeneous behavioral feedback. The model treats observed behaviors as noisy measurements of a low-dimensional, factorized latent value state and uses structured output heads to model heterogeneous feedback signals. A restricted baseline path captures predictable variation from measurement-confounding features such as video duration, user propensity, and session context, while a routed latent path estimates preference-relevant value advantage. The resulting latent value score can be integrated into an existing recommender system as a ranking feature or ranking score. On YouTube Shorts, a major short-form video platform, this model improves offline metrics and lifts a primary viewer enjoyment metric by 2.67% in online A/B tests.

Abstract: Video diffusion transformers produce high-quality videos, yet iterative denoising incurs substantial inference latency, limiting interactive and large-scale serving. Most existing acceleration methods focus on individual requests, thereby restricting efficiency gains to redundancy within a single generation trajectory. Recent cross-request reuse offers an additional source of savings, but existing approaches often infer reusability from coarse semantic similarity. This conflates semantic relatedness with generation-level computational compatibility, so aggressive reuse may accept incompatible historical computation while conservative reuse leaves substantial acceleration unrealized. We present \emph{Carnator}, a cross-request acceleration framework that addresses this challenge by extracting and using generation-native compatibility evidence directly from the model's evolving internal states. Specifically, \emph{Carnator} performs a lightweight early probe to construct an Early Signature from internal diffusion states, assessing reuse validity through risk-aware compatibility decisions. The same evidence characterizes reuse scope by localizing target-specific computation and guiding joint reuse of historical latent trajectories and sparse attention connectivity. Across three text-to-video backbones, Carnator consistently achieves higher cache-hit end-to-end acceleration than the evaluated cross-request baselines despite more selective cache acceptance, reaching up to 2.17$\times$ speedup while maintaining competitive generation quality.

Abstract: Spatio-Temporal Video Grounding (STVG) aims to localize the spatio-temporal tube in a video corresponding to a natural language query. While recent methods achieve strong performance in fully supervised, weakly supervised, and zero-shot settings, they typically rely on computationally expensive architectures, complex training pipelines, or multimodal large language models. We present Pocket-STVG (P-STVG), a lightweight cascade architecture that addresses STVG by combining efficient pre-trained components instead of large end-to-end models. P-STVG integrates a temporal-aware video encoder based on MobileViCLIP, a spatial encoder-decoder derived from MDETR, and a shared aligned text encoder. Temporal localization is performed through either a lightweight 1D U-Net or a simple thresholding strategy, enabling the same framework to operate in both weakly supervised and zero-shot settings. Furthermore, video representations are precomputed independently of the query, yielding an indexing-friendly pipeline for efficient inference and large-scale video collections. Despite requiring fewer than 90M parameters, P-STVG performs on par with weakly supervised methods and improves on earlier zero-shot approaches at a fraction of their memory and computational cost, establishing a favorable performance-efficiency trade-off for STVG.

Abstract: Watch time is the primary engagement signal in short video feeds, and its prediction directly affects ranking and exposure. Existing methods improve watch time prediction by correcting duration bias or modeling richer distributions, but most expose only an expected or debiased watch time at serving time. Even when video duration is available to later models, the interface gives only one estimate of watch time and no probabilities for completion, overplay, or other regions relevant to downstream tasks. To address this limitation, we propose the Distributional Serving Interface (DSI), which has a distribution provider, a compact, low-dimensional summary, and lightweight readouts tailored to each task. The provider learns a joint distribution over four watch states derived from watch ratio and their event times; rules based on video duration remove incompatible combinations, while a restoration loss preserves accuracy in seconds. The summary reduces this distribution to a small set of event probabilities, time scales relative to duration, and uncertainty statistics. After training the provider, we fix its parameters and train value and ranking readouts that combine the summary with raw context. Across KuaiRec, KuaiRand-1K, and WeChat21, the complete DSI system achieves the lowest MAE on all three datasets, beating the strongest result among nine baselines by 1.9% to 8.5%, and achieves the best XAUC on two. It also leads retrieval metrics that account for video duration when complete systems are compared. With matched readouts held constant, the summary retains information relevant to each task beyond a predicted mean paired with video duration. Using the same lightweight linear heads for each new target, it also performs best on two new watch-time targets and improves a separately logged engagement target, while a randomly initialized provider does not reproduce this gain.

Abstract: Industrial mobile feed systems rely on a retrieval-ranking pipeline to serve large-scale, heterogeneous, and fast-changing content under strict latency constraints. However, existing pipelines still suffer from two critical issues: hierarchical quantization instability in candidate retrieval and information loss between separated retrieval and ranking stages. These issues hurt long-tail and cold-start recommendation and complicate efficient serving. To address them, we present UNIQUE, a unified retrieval and ranking recommendation framework with single-layer flat quantization. UNIQUE integrates generative code-based retrieval and target-aware ranking into one early-fusion architecture, enabling end-to-end training under a shared representation while preserving efficient candidate generation. A balanced quantization mechanism is further introduced to mitigate codebook imbalance and improve long-tail representation. Offline experiments evaluate UNIQUE from both retrieval and ranking perspectives, while codebook analysis shows more balanced resource allocation than hierarchical quantization. We deploy UNIQUE in the homepage feed, discovery-page, and short-video recommendation scenarios of Mobile Baidu, serving large-scale real-world traffic. Online A/B tests achieve a 0.96% gain in total watch duration and a 1.08% gain in total distribution volume, with notable improvements for new users and highly active users. Serving measurements show 89 ms P99 latency and 44.23% online inference MFU. These results show that UNIQUE provides a stable, efficient, and production-ready framework for unified retrieval and ranking in industrial recommendation.

Abstract: Large language model (LLM) agents can propose, implement, and evaluate model changes. Autoresearch loops demonstrate this capability through minutes-scale iterations on a self-contained program. Online autoresearch instead spans asynchronous systems, hours-long variants, and weeks-long campaigns that can influence a product. A completed run can still support an invalid conclusion when a code change is a no-op, data windows leak, evaluator semantics drift, or the two arms traverse different serving funnels. We present EvoPilot, a human-gated method for long-horizon online autoresearch. Role-specific agents execute each round through a versioned domain skill and typed adapter. Durable records preserve experiments and failures; deterministic checks enforce recorded lessons. We study a 37-day campaign for the retrieval system that powers Video Deep Dive (VDD), an online experience for discovering follow-on videos after a user opens a seed video. The campaign covered seven directions and used an hourly refreshed index of hundreds of millions of videos. Earlier manual experiments had not established a benefit from an interaction head. A primitive autoresearch attempt revisited the direction but incorrectly attributed an offline hit-rate decline of 22 percentage points to the head. We then introduced EvoPilot. Its human-gated verification traced the drop to a pre-existing evaluation defect that produced output depths of 3,000 and 600. After repair, a matched comparison measured an offline improvement of 3.20 percentage points. Post-study replay and mutation tests rejected invalid comparisons while admitting valid counterparts. Durable state recovered an interrupted round, and artifact reuse avoided approximately five GPU-hours. Separately, a seven-day randomized online evaluation estimated a 0.66% relative increase in the VDD slice of Good Search Result Rate for Retention (GSRR).

Abstract: As streaming services become more commonplace, analyzing their behavior effectively under different network conditions is crucial. This is normally quite expensive, requiring multiple players with different bandwidth configurations to be emulated by a powerful local machine or a cloud environment. Furthermore, emulating a realistic network behavior or guaranteeing adherence to a real network trace is challenging. This paper presents PyStream, a simple yet powerful way to emulate a video streaming network, allowing multiple simultaneous tests to run locally. By leveraging a network of Docker containers, many of the implementation challenges are abstracted away, keeping the resulting system easily manageable and upgradeable. We demonstrate how PyStream not only reduces the requirements for testing a video streaming system but also improves the accuracy of the emulations with respect to the current state-of-the-art. On average, PyStream reduces the error between the original network trace and the bandwidth emulated by video players by a factor of 2-3 compared to Wondershaper, a common network traffic shaper in many video streaming evaluation environments. Moreover, PyStream decreases the cost of running experiments compared to existing cloud-based video streaming evaluation environments such as CAdViSE.

Abstract: The remarkable success of large language models (LLMs) has provided important inspiration for the next generation of recommender systems. Structurally, recommendation and language generation share a similarity: both aim to produce an ordered sequence that optimizes the user's experience. However, how to precisely absorb the essence of the LLM paradigm into mature industrial recommender systems remains an open problem. There are two challenges. First, it is unclear how to incorporate sequence-level generation and optimization from the LLM paradigm into recommendation. Second, real-world recommender systems are mature systems that have been iteratively customized for years around specific products, business constraints, serving infrastructure, and organizational ownership. Replacing such systems wholesale is often technically risky and organizationally disruptive. In this paper, we propose LIGE-GR, a listwise generation and evaluation recommendation framework that upgrades from a traditional ranking system based on itemwise recommendation toward a generative recommendation paradigm. Instead of rebuilding the entire recommendation stack from scratch, LIGE-GR generalizes the existing pointwise recommendation system into a listwise generation system. This allows mature recommender systems to benefit from listwise optimization while preserving compatibility with existing models, value functions, and serving infrastructure. We validate LIGE-GR in short-video recommendation on Instagram Reels and Facebook Video. On these recommendation surfaces, LIGE-GR improves time spent by 1.14 percent on Instagram Reels and 0.72 percent on Facebook Video, while requiring only modest additional inference resources.

Abstract: Scaling Multimodal Large Language Models (MLLMs) to long-form video understanding is bottlenecked by the explosion of visual tokens, which saturates context windows and incurs prohibitive costs. Current solutions predominantly rely on auxiliary models for token reduction but face a fundamental dilemma: lightweight encoder-driven approaches often overlook critical semantic information, whereas heavyweight MLLM-driven reduction negates the efficiency gains. {In this work, we identify a more fundamental inefficiency underlying this dilemma: while fine-grained visual details are essential for detailed understanding, they are largely redundant for the preliminary task of selecting semantically relevant regions. } Motivated by this, we introduce \textbf{VideoMM}, which marks a paradigm shift from model-centric downsizing to adaptive perceptual granularity. Specifically, our framework {decouples selection from reasoning} by executing semantic filtering on a cost-effective \textit{Macro Proxy} (derived from downscaled frames), and projecting the selected regions onto high-fidelity \textit{Micro Tokens} for detailed understanding only when necessary. Extensive evaluations show that VideoMM significantly outperforms existing solutions. It achieves a 6.13$\times$ speedup and a 7.4\% accuracy gain over full-context baselines on LongVideoBench, and further accelerates inference by 2.73$\times$ over current leading methods, establishing a highly scalable paradigm for long-video understanding. Our code is available at: https://github.com/adfh917k/VideoMM.

Abstract: Detecting video highlights, the most informative or engaging moments in a video, is important for applications such as video summarization and content recommendation. We propose a zero-shot framework that combines CLIP, large language models (LLMs), and diffusion models. Given lightweight video metadata, such as a title or category, an LLM generates textual descriptions of likely highlight events. These descriptions are further converted into synthetic visual prototypes using a diffusion model. Textual and visual representations are matched to video frames using CLIP, enabling frame-level highlight detection without highlight annotations or dataset-specific training. Experiments on TVSum and SumMe demonstrate strong zero-shot performance, with particularly favorable results on TVSum. The proposed approach provides an effective framework for metadata-conditioned zero-shot video highlight detection.

Abstract: The rise in the number and diversity of available software development video tutorials has enhanced digital learning for developers but also introduced challenges in locating relevant content efficiently. Existing video search methods, including keyword-based approaches and tools like CodeTube and TechTube, rely primarily on retrieval algorithms such as BM25, which fail to capture the semantic nuances and user intentions behind search queries. To address these limitations, we introduce ISM, an approach that uses SBERT to generate semantically rich vectors from video tutorial transcripts to improve the search for programming video tutorials. By segmenting transcripts and implementing a re-ranking process, ISM effectively preserves context and enhances the relevance of search results. Additionally, ISM generates informative video summaries using GPT-4, allowing developers to quickly assess the relevance of video content. To evaluate our approach, we first performed a quantitative study comparing ISM with the baseline TechTube. The results revealed that ISM performs better in both video retrieval and fragment identification, achieving a Hit@5 score of 0.95 and an average F1 score of 0.70 compared to the baseline's 0.58 and 0.52, respectively. We also performed a user study, which revealed that users strongly preferred the semantic matching capabilities and AI-generated summaries of our approach. This work advances the state-of-the-art in programming video tutorial search and summarization by offering more nuanced and user-aligned retrieval and summarization mechanisms.

Abstract: Composed video retrieval (CoVR) searches a gallery for the target video that realizes a natural-language modification of a source clip. However, at gallery scale, this creates a fundamental tension: compact embeddings enable efficient, reusable search but can miss the transient actions, state changes, and subtle constraints that demand fine-grained video reasoning, whereas applying large multimodal models uniformly sacrifices scalability. To address these limitations, we propose that frozen foundation models should instead occupy complementary roles, with inference depth adapted to query difficulty. Based on this premise, we introduce \methodname{}, a framework for training-free \methodexpansion{}. Specifically, a composed-query embedding first searches reusable video-only gallery representations; uncertain queries undergo bounded reranking and candidate expansion; ambiguous edits trigger target-description generation; and only close leading candidates reach multimodal verification. To support these roles, frame selection, spatial resolution, and time cues are adapted to each stage. Across complete target-gallery evaluations, our method reaches state-of-the-art performance among training-free approaches, with 89.55 and 93.43 R@1 on Dense-WebVid-CoVR and CoVR-R, respectively (with more than +35\% and +25\% absolute margins to the closest counterpart). These results show that adaptively orchestrating foundation-model capabilities can combine scalable retrieval with fine-grained reasoning without task-specific training. The source code and all relevant guidelines are available on https://github.com/demidovd98/CoVRAGE.