activity
20232026
most citedInvestigating and Mitigating the Multimodal Hallucination Snowballing in Large Vision-Language Models

1 citations · 1 across the 18 of their papers we have counts for

collaborators

22 papers

cs.CL2026

ACTD: Anchor-Based Cross-Tokenizer Distillation with Residual Regularization

Huiyi Zhang, Zijian Li, Xiaocheng Feng +4

Knowledge distillation effectively transfers reasoning capabilities from large language models to lightweight student models. To enable knowledge transfer across disparate model fa…

cs.AI2026

SAVOIR: Learning Social Savoir-Faire via Shapley-based Reward Attribution

Xiachong Feng, Yi Jiang, Xiaocheng Feng +9

Social intelligence, the ability to navigate complex interpersonal interactions, presents a fundamental challenge for language agents. Training such agents via reinforcement learni…

cs.AI2026

Stratagem: Learning Transferable Reasoning via Trajectory-Modulated Game Self-Play

Xiachong Feng, Deyi Yin, Xiaocheng Feng +9

Games offer a compelling paradigm for developing general reasoning capabilities in language models, as they naturally demand strategic planning, probabilistic inference, and adapti…

cs.CL2026

x1: Learning to Think Adaptively Across Languages and Cultures

Yangfan Ye, Xiaocheng Feng, Xiachong Feng +8

Languages encode distinct abstractions and inductive priors, yet most large language models (LLMs) overlook this diversity by reasoning in a single dominant language. In this work,…

cs.AI2026

ImplicitMemBench: Measuring Unconscious Behavioral Adaptation in Large Language Models

Chonghan Qin, Xiachong Feng, Weitao Ma +2

Existing memory benchmarks for LLM agents evaluate explicit recall of facts, yet overlook implicit memory where experience becomes automated behavior without conscious retrieval. T…

cs.CL2026

Silence the Judge: Reinforcement Learning with Self-Verifier via Latent Geometric Clustering

Nonghai Zhang, Weitao Ma, Zhanyu Ma +5

Group Relative Policy Optimization (GRPO) significantly enhances the reasoning performance of Large Language Models (LLMs). However, this success heavily relies on expensive extern…