8 papers
Thinking Economically: A Hierarchical Framework for Adaptive-Complexity Reasoning in LLMs
Yubo Gao, Haotian Wu, Hong Chen +8
Chain-of-Thought (CoT) has significantly enhanced LLM reasoning, yet often incurs substantial computational overhead due to "overthinking": generating excessively long rationales w…
AndroTMem: From Interaction Trajectories to Anchored Memory in Long-Horizon GUI Agents
Yibo Shi, Jungang Li, Linghao Zhang +25
Long-horizon GUI agents are a key step toward real-world deployment, yet effective interaction memory under prevailing paradigms remains under-explored. Replaying full interaction…
Temporal Gains, Spatial Costs: Revisiting Video Fine-Tuning in Multimodal Large Language Models
Linghao Zhang, Jungang Li, Yonghua Hei +12
Multimodal large language models (MLLMs) are typically trained in multiple stages, with video-based supervised fine-tuning (Video-SFT) serving as a key step for improving visual un…
RTV-Bench: Benchmarking MLLM Continuous Perception, Understanding and Reasoning through Real-Time Video
Shuhang Xun, Sicheng Tao, Jungang Li +11
Multimodal Large Language Models (MLLMs) have made rapid progress in perception, understanding, and reasoning, yet existing benchmarks fall short in evaluating these abilities unde…
MOSS-ChatV: Reinforcement Learning with Process Reasoning Reward for Video Temporal Reasoning
Sicheng Tao, Jungang Li, Yibo Yan +8
Video reasoning has emerged as a critical capability for multimodal large language models (MLLMs), requiring models to move beyond static perception toward coherent understanding o…
Unveiling Instruction-Specific Neurons & Experts: An Analytical Framework for LLM's Instruction-Following Capabilities
Junyan Zhang, Yubo Gao, Yibo Yan +8
The finetuning of Large Language Models (LLMs) has significantly advanced their instruction-following capabilities, yet the underlying computational mechanisms driving these improv…