collaborators

10 papers

cs.CV2026

The Perceptual Bandwidth Bottleneck in Vision-Language Models: Active Visual Reasoning via Sequential Experimental Design

Anjie Liu, Ziqin Gong, Yan Song +6

Visual perception in modern Vision-Language Models (VLMs) is constrained by a perceptual bandwidth bottleneck: a broad field of view preserves global context but sacrifices the fin…

cs.CL2026

Correct Answers from Sound Reasoning: Verifiable Process Supervision for Language Models

Kyuyoung Kim, Kevin Wang, Yunfei Xie +7

Training language models to produce both correct answers and sound reasoning remains an open challenge. Reinforcement learning with verifiable rewards typically optimizes only fina…

cs.AI2026

MiroEval: Benchmarking Multimodal Deep Research Agents in Process and Outcome

Fangda Ye, Yuxin Hu, Pengxiang Zhu +19

Recent progress in deep research systems has been impressive, but evaluation still lags behind real user needs. Existing benchmarks predominantly assess final reports using fixed r…

cs.CL2026

LexInstructEval: Lexical Instruction Following Evaluation for Large Language Models

Huimin Ren, Yan Liang, Baiqiao Su +4

The ability of Large Language Models (LLMs) to precisely follow complex and fine-grained lexical instructions is a cornerstone of their utility and controllability. However, evalua…

cs.AI2026

PyVision-RL: Forging Open Agentic Vision Models via RL

Shitian Zhao, Shaoheng Lin, Ming Li +4

Reinforcement learning for agentic multimodal models often suffers from interaction collapse, where models learn to reduce tool usage and multi-turn reasoning, limiting the benefit…

cs.AI2026

SPAN: Benchmarking and Improving Cross-Calendar Temporal Reasoning of Large Language Models

Zhongjian Miao, Hao Fu, Chen Wei

We introduce SPAN, a cross-calendar temporal reasoning benchmark, which requires LLMs to perform intra-calendar temporal reasoning and inter-calendar temporal conversion. SPAN feat…