multimedia application developers

Abstract: We present Youtu-Parsing-Omni, an omni-modal parser that converts documents, images, audio, and video into structured records grounded in space and time, providing a perception layer for agents that read, locate, and cite evidence across modalities. Its design rests on one encoder for every modality and one schema for every task. Youtu-Omni-Encoder, initialized from a pre-trained language model to strengthen text reading, encodes all modalities with shared weights in a unified space-time coordinate system, and a few fusion layers let video frames attend to concurrent audio, bringing cross-modal fusion and temporal alignment into perception itself. OmniSchema unifies the outputs of all ten parsing tasks, allowing a single self-evolving post-training procedure, OmniSchema-Aware On-Policy Distillation (OSAD), to provide a shared token-role-based objective across tasks. In each round, the model is trained on its own rollouts against token-level targets from a reference-conditioned copy of itself, which is then refreshed with the trained weights, so that the parser and its supervision co-evolve. With a single 5 B-parameter checkpoint, Youtu-Parsing-Omni achieves state-of-the-art performance on OmniDocBench v1.6 (96.96 Overall) and leads all open-weight models on OmniParsingBench (75.08 Avg.), with its advantage concentrated on audio and video. It also achieves the best overall chart-parsing score (95.02) and the highest exact chemical-fingerprint agreement among compared systems, and matches a dedicated optical-music model in character-level transcription of typeset sheet music while staying far ahead of general-purpose systems. Code and model weights are publicly available.

Abstract: Distributed vector stores increasingly serve multimodal workloads whose representations are jointly accessed but independently partitioned and placed. As a result, cross-modal physical locality remains largely unoptimized. Multimodal queries can incur remote accesses and cross-tier data movement even when each modality's ANN search remains efficient. We present Coloc, a storage-management layer that makes cross-modal access locality a first-class data-layout signal. A Cross-Modal Access Graph combines semantic affinity, co-access, and temporal behavior. A movement-aware optimizer places frequently co-accessed vectors under capacity and topology constraints. A migration manager adapts placement as workloads shift by weighing locality gains against migration cost. A confidence-gated prefetcher hides remaining slow-tier latency. Coloc operates above existing ANN indexes without modifying embeddings, search, or retrieval semantics. We deploy Coloc on a multi-tier AWS testbed spanning GPU, NUMA-DRAM, NVMe, and S3. Coloc substantially reduces data movement and query latency while leaving ANN retrieval unchanged. Under a scheduled workload shift, its migration manager matches the locality of periodic global reorganization while moving 5.9x less data and completing 3.9x faster.

Abstract: Most unified multimodal models treat images and text asymmetrically: a pretrained language model generates text, an attached diffusion head generates images, and outputs that contain both are produced in a fixed order, so the first output cannot adapt to the second. We ask whether both modalities can instead be generated by one process that is trained on them jointly from scratch. Pretrained encoder spaces hold both modalities in one continuous form and carry knowledge learned at scale, and recent work finds them effective as generative targets for vision and language. We therefore model the joint distribution directly in these spaces. We introduce JUICE (Joint Unified multimodal modeling In Continuous Encoder spaces), a single flow matching Transformer over frozen image and text representations, in which each modality has its own noise level. Which modalities are clean and which are generated then decides the task: image generation, captioning, visual question answering, or joint generation. Controlled pretraining runs test each design choice. At equal guidance, generating text as continuous states leaves image generation intact (48.41 GenEval, against 47.86 for a model trained only for text-to-image generation), while captions lose some exact wording. Training on joint and conditional denoising together beats either alone, and semantic encoder spaces beat VAE latents and raw pixels as targets. At 2.1B parameters, with no language model initialization and at 224x224, JUICE reaches up to 0.88 on GenEval and 73.1 on VQAv2. By sampling both modalities from the joint distribution (coupled sampling), it can also draw a route on a map while writing out the matching moves. On mazes with several valid solutions, joint success rises from 54.6% with independent sampling to 93.7%, and no modality has to go first. On visual spatial planning, JUICE solves 99.8% of maps at its training sizes.

Abstract: Any-to-any generation seeks a single model that translates flexibly among text, image, and audio, yet existing approaches either require fully aligned multimodal tuples or a shared representation that suppresses modality-specific structure. We introduce Modaliff, a novel token-based diffusion model that learns from widely available bimodal pairs while preserving each modality in its native latent sequence. Modaliff assembles conditions and targets into a unified token sequence, with per-token attributes to disambiguate token identities and role-based positional embedding to preserve each modality's internal structure across sequence layouts. This design enables a single denoiser to support diverse generation tasks without task-specific architectural changes or a shared cross-modal latent space. Beyond one-to-one generation, Modaliff supports multiple conditions either by combining single-condition predictions at inference or by lightweight finetuning on captions that jointly describe multiple inputs. Experiments across text, image, and audio show that Modaliff achieves the best fidelity among any-to-any models on most generation tasks while using substantially fewer parameters and training data.

Abstract: Understanding human emotion is essential for multimodal systems that interpret both the content of an interaction and the speaker's expressive state. However, connecting paralinguistic cues to generated answers remains challenging, particularly when vocal expression diverges from visual appearance. We propose DualAffect, a dual-path architecture that integrates visually conditioned acoustic features and temporally organized acoustic tokens into a shared language decoder. The two pathways reuse the same acoustic encoding. The fusion pathway associates sound with visual content through visual queries, while the direct pathway compresses the valid acoustic sequence into ordered tokens through an independent projector. This design gives the decoder access to both joint audiovisual context and acoustic evidence organized along its own timeline. Mixed-task adaptation with task-dependent output preservation supports emotion recognition and general audiovisual question answering within the same model. DualAffect achieves an average metric of 67.89 on CA-MER and accuracies of 62.88% on the EmotionTalk test set and 49.87% on Daily-Omni. Pathway interventions show that the trained decoder uses direct acoustic evidence alongside existing fusion. With model parameters and fusion inputs fixed, zeroing the direct tokens reduces EmotionTalk validation accuracy by 9.75 percentage points and the CA-MER average metric by 2.66 points. The largest CA-MER subset effect occurs when the overall emotion agrees with audio but differs from vision. These findings identify acoustic representation organization as a practical design axis for connecting paralinguistic perception to unified audiovisual generation. Code is available at https://github.com/YiboWang2002/DualAffect.

Abstract: Vision-Language Models (VLMs) have shown strong multimodal reasoning capabilities, yet whether they truly capture the physical consistency underlying real-world dynamics remains unclear. Existing benchmark paradigms often suffer from fragmented evaluation, focusing on isolated cognitive stages while overlooking the inherent synergy between perception, reasoning, and physical judgment. The lack of a holistic perspective limits the ability to diagnose whether VLMs can reliably evaluate the physical authenticity of emerging generative models. To address these issues, we introduce PhysVista, a benchmark designed to evaluate physical intelligence in VLMs through a closed cognitive loop framework inspired by the human seeing-reasoning-assessment process. PhysVista restores this loop by jointly evaluating physical state perception, physical dynamics reasoning, and physical plausibility assessment. It further distinguishes event-level reasoning and scale-level reasoning to enable fine-grained analysis of physical understanding. In addition, PhysVista incorporates both real-world and AI-generated videos, allowing evaluation across diverse domains and emerging generative scenarios. Extensive experiments across a diverse set of VLMs reveal substantial limitations in physical reasoning and plausibility assessment, highlighting a persistent gap between visual recognition and genuine physical understanding, and pointing toward more principled designs for physically grounded multimodal intelligence.

Abstract: Audio-visual large language models (AVLLMs) have made remarkable progress in multimodal understanding and reasoning through interactions among visual, auditory, and linguistic information. However, recent studies show that AVLLMs face a critical challenge: $\textbf{source-confused grounding hallucination}$, where cues from the unused modality induce responses that the required modality does not support, undermining reliability in real-world applications. Existing methods have made progress in mitigating this failure, yet how it arises from internal cross-modal interactions remains insufficiently understood. To address this gap, we conduct path-intervention and representation analyses, revealing a $\textbf{question-relay}$ mechanism: question states carry interfering cues alongside required-source evidence, undermining grounding in required-modality evidence. Cutting pathways from interfering modality to question states yields greater correct-answer logit recovery than cutting those to the generation position. Motivated by these findings, we propose $\textbf{SECRET}$ ($\textbf{S}$ourc$\textbf{E}$-$\textbf{C}$onditioned $\textbf{RE}$lay s$\textbf{T}$eering), a training-free method that mitigates cross-modal interference at the question relay. Using contrasting question representations elicited through different modality-pathway interventions, SECRET steers the original question states toward required-source evidence. Experiments on two widely adopted benchmarks CMM and AVHBench across three AVLLMs show that SECRET consistently outperforms prior training-free methods, substantially mitigating source-confused grounding hallucinations (e.g., up to +18.0 and +7.1 percentage points over base models). Modality-specific captioning further demonstrates its generalizability to open-ended generation.

Abstract: As Omni-modal large language models (Omni-LLMs) take in audio, video and text together, their KV cache memory cost grows. KV cache quantization is the de facto approach in text-only LLMs, but its application to Omni-LLMs remains unexplored. In this paper, we analyze how TurboQuant, a representative rotation-based KV cache quantization method, behaves on multimodal caches and identify two critical issues: temporal key drift and heterogeneous value geometry. To address these, we propose OmniKVQuant, a training-free framework that (i) sets the key quantization range over each short window of the input stream; and (ii) rotates values separately per modality. On Qwen2.5-Omni and Qwen3-Omni, OmniKVQuant enables 2-bit KV caches while substantially preserving performance across seven audio-visual benchmarks. We further provide a fused Triton decode kernel that unpacks the 2-bit cache during attention, so no dense FP16 cache is ever built. Code: https://github.com/kaistmm/OmniKVQuant