collaborators

11 papers

cs.CV2026

Homer: Understanding Long-form Videos with Hierarchical Memory and Agentic Reasoning

Yixin Ji, Fanghua Ye, Juntao Li +5

Multimodal large language models excel on short clips but struggle on hour-long videos in an online setting, where frames are processed incrementally under limited memory. Existing…

cs.CV2026

AffectVerse: Emotional World Models for Multimodal Affective Computing

Bo Zhao, Fanghua Ye, Yixin Ji +3

Humans infer emotions by integrating observed multimodal cues with expectations about how affective states may unfold. Existing multimodal large language models (MLLMs), however, o…

cs.AI2026

When to Vote, When to Rewrite: Disagreement-Guided Strategy Routing for Test-Time Scaling

Zhimin Lin, Yixin Ji, Jinpeng Li +5

Large Reasoning Models (LRMs) achieve strong performance on mathematical reasoning tasks but remain unreliable on challenging instances. Existing test-time scaling methods, such as…

cs.CL2026

When to Trust Tools? Adaptive Tool Trust Calibration For Tool-Integrated Math Reasoning

Ruotao Xu, Yixin Ji, Yu Luo +5

Large reasoning models (LRMs) have achieved strong performance enhancement through scaling test time computation, but due to the inherent limitations of the underlying language mod…

cs.CL2026

When Is Thinking Enough? Early Exit via Sufficiency Assessment for Efficient Reasoning

Yang Xiang, Yixin Ji, Ruotao Xu +4

Large reasoning models (LRMs) have achieved remarkable performance in complex reasoning tasks, driven by their powerful inference-time scaling capability. However, LRMs often suffe…

cs.LG2026

GAST: Gradient-aligned Sparse Tuning of Large Language Models with Data-layer Selection

Kai Yao, Zhenghan Song, Kaixin Wu +5

Parameter-Efficient Fine-Tuning (PEFT) has become a key strategy for adapting large language models, with recent advances in sparse tuning reducing overhead by selectively updating…