12 papers
BayesJudge: Uncertainty-Aware Bayesian Meta-Evaluation of Human and LLM Judgments
Jiahao Zhang, Pengbin Feng, Chunlei Meng +2
AI evaluation pipelines often produce conflicting judgments rather than clean labels. In pairwise LLM evaluation, this conflict is especially visible: disagreement can arise from a…
Zero2Repo: Can Coding Agents Build Repositories from Scratch?
Pei Yang, Tianyu Shi, Yuhang Yao +23
Coding agents are increasingly asked to build software rather than patch it, yet benchmarks for from-scratch repository construction are mostly limited to a single language and dep…
Adaptive Hierarchical Representation Alliance for Multimodal Learning
Chunlei Meng, Pengbin Feng, Jacqueline J. Pang +5
Multimodal models often align language, vision, and audio in a single final-layer latent space, implicitly assuming that task-relevant evidence emerges at the same semantic depth a…
Rethinking Modality Reliability in Multimodal Sentiment Analysis with Incomplete Observations
Chunlei Meng, Jacqueline J. Pang, Pengbin Feng +3
Multimodal Sentiment Analysis (MSA) integrates text, audio, and vision to infer human affect, yet real-world multimodal observations are often incomplete. Existing methods for inco…
Second-Order Response Laws for LLM Judges: Debiased Estimation of Prompt Instability
Pengbin Feng, Chunlei Meng, Daozheng Qu +3
LLM judges are often evaluated with a single prompt and only a few repeated calls. When their verdicts vary, it remains unclear whether the variation comes from sampling noise with…
Scaling Laws for Collapse in Asynchronous GRPO
Jingwei Song, Haofeng Xu, Jie Xiao +10
Asynchronous reinforcement learning improves the throughput of large language model post-training by decoupling rollout generation from policy optimization, but introduces a mismat…
MOSAIC: Orchestrating Collaborative Knowledge Tracing with Hierarchical Semantic Alignment
Xinjin Li, Mengyue Wang, Yuzhen Lin +4
Knowledge Tracing (KT) is important for personalized education but traditionally suffers from two key limitations: a reliance on shallow ID-based representations that neglect seman…
CACR:Reinforcing Temporal Answer Grounding in Instructional Video via Candidate-Aware Causal Reasoning
Muge Qi, Rong Fu, Pengbin Feng +7
The task of temporal answer grounding in instructional video (TAGV), which aims to locate precise video segments that respond to natural language queries, is increasingly important…
TwinRouterBench: Fast Static and Live Dynamic Evaluation for Realistic Agentic LLM Routing
Pei Yang, Wanyi Chen, Tongyun Yang +15
LLM routing matters most in long-horizon applications such as coding agents, deep research systems, and computer-use agents, where a single user request triggers many model calls.…
Group Cognition Learning: Making Everything Better Through Governed Two-Stage Agents Collaboration
Chunlei Meng, Pengbin Feng, Rong Fu +7
Centralized multimodal learning commonly compresses language, acoustic, and visual signals into a single fused representation for prediction. While effective, this paradigm suffers…
Mitigating Shared-Private Branch Imbalance via Dual-Branch Rebalancing for Multimodal Sentiment Analysis
Chunlei Meng, Jiabin Luo, Pengbin Feng +4
Multimodal Sentiment Analysis (MSA) requires integrating language, acoustic, and visual signals without sacrificing modality-specific sentiment evidence. Existing methods mainly im…
CrowdVLM-R1: Expanding R1 Ability to Vision Language Model for Crowd Counting using Fuzzy Group Relative Policy Reward
Zhiqiang Wang, Pengbin Feng, Yanbin Lin +4
We propose Fuzzy Group Relative Policy Reward (FGRPR), a novel framework that integrates Group Relative Policy Optimization (GRPO) with a fuzzy reward function to enhance learning…