4 citations · 13 across the 11 of their papers we have counts for
6 papers · 1 filter
From Tasks to Turns: Measuring Human Labor Contributions in Human-Agent Joint Production
Likai Wang, Dezhao Su, Jing Hu +3
In agent workflows, a brief human instruction can alter subsequent search, reasoning, and tool execution, yet final task outcomes rarely reveal the contribution of an individual in…
We Query, Therefore We Compute: On Oracle Computation beyond the Machine, with an Application to Agents
Kefan Liu, Fengning Ou, Yelin Luo +1
Agentic systems use large language models (LLMs) to carry out concrete tasks. Prior work often borrows abstractions such as scheduling, caching or isolation piecemeal from operatin…
Just MLPs: Efficient Visual State Reconstruction for Multimodal Language Models
Jingdi lei, Junxian Li, Di Zhang +3
Long visual token sequences often account for a substantial fraction of the computational overhead in multimodal large language models~(MLLMs). Existing approaches reduce this cost…
Memorize Theorems, Not Instances: Probing SFT Generalization through Mathematical Reasoning
Ruiying Peng, Mengyu Yang, Jing Lei +3
Supervised Fine-Tuning (SFT) is widely used for task-specific adaptation, yet recent work shows it systematically undermines reasoning generalization. We argue the root cause is no…
-mem: Efficient Online Memory for Large Language Models
Jingdi Lei, Di Zhang, Junxian Li +7
Large language models increasingly need to accumulate and reuse historical information in long-term assistants and agent systems. Simply expanding the context window is costly and…
Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models
Ruiying Peng, Xueyu Wu, Jing Lei +3
Multimodal large language models (MLLMs) often suffer from perceptual impairments under extended reasoning modes, particularly in visual question answering (VQA) tasks. We identify…