Papers for

mobile ai engineers

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Client selection improves federated multimodal model fine-tuning under network limits

CARE-FL: Federated Fine-Tuning of Multimodal LLMs in Resource-Constrained Edge Networks

Abstract: Domain-specific adaptation of Multimodal Large Language Models (MLLMs) in privacy-sensitive edge environments requires federated fine-tuning, yet client selection remains challenging due to heterogeneous multimodal data and modality availability, dynamic system conditions, and evolving client utility during training. We propose Constraint-Aware Reinforcement Learning for Efficient Federated Fine-Tuning (CARE-FL), a constrained online client-selection framework for federated MLLM Low-Rank Adaptation (LoRA) fine-tuning. CARE-FL formulates client participation as a sequential decision process and employs Q-value decomposition to address the large combinatorial joint action space through scalable client-level long-term utility estimation. These utilities are learned online using a modified Double Deep Q-Learning (DDQL) scheme, while constraint-aware $ε$-greedy execution selects feasible client subsets under per-round latency and bandwidth constraints. Complementing client selection, an adaptive aggregation mechanism further controls potentially unstable global updates and places greater weight on the previous model when needed. Experiments on the CrisisMMD disaster-response task in emulated heterogeneous wireless edge environments show that CARE-FL achieves higher and more stable test accuracy than the compared client-selection baselines across different system settings, while satisfying the imposed latency and bandwidth constraints.

Wed 4 NovDistributed, Parallel, and Cluster Computing
The gist
Training large language AI models that understand images and text together is hard when data is spread across different devices that have different connection speeds and data types. The paper offers a new way to pick which devices should help train the model so the process is faster and uses less network data. Their method learns over time which devices to choose, balancing speed and bandwidth limits. Tests show it gives better and more stable AI performance on disaster response tasks than older methods.
Open → 2611.06169v1

HyperThink speeds up multi-step reasoning in large language models

HyperThink: Text-to-Parameter Hypernetworks for Efficient Reasoning

Abstract: Long-form thinking traces can substantially improve the multi-step reasoning performance of large language models (LLMs), but they introduce high inference-time overhead, with latency dominated by sequential decoding. We propose HyperThink, a text-to-parameter approach that amortizes this reasoning computation into a single query-conditioned parameter update: a lightweight hypernetwork reads the question and predicts updates to a small subset of the base LLM's parameters, while a vector-quantized decoder constrains them to a finite set of reusable patterns to improve robustness and transfer. Trained end-to-end on outputs from the base model itself, HyperThink eliminates long thinking traces at test time: after one hypernetwork forward pass, the adapted model generates a concise step-by-step solution and final answer without an intermediate trace, using far fewer tokens while retaining strong reasoning performance. Empirically, HyperThink improves the low-latency region of the accuracy-latency trade-off on mathematical and general reasoning tasks, with its strongest gains in the near-non-thinking regime.

Fri 2 OctComputation and LanguageMachine Learning
The gist
Reasoning through complex problems with large language models usually takes a long time because they think step-by-step slowly. The authors created HyperThink, a system that quickly adjusts a small part of the model based on the question, so it can give a detailed answer fast without showing all the steps. This makes the model faster at reasoning while keeping its accuracy. HyperThink learns by looking at the normal model’s answers but uses fewer words and less time when actually solving problems.
Open → 2610.03039v1