6 papers
SiameseNorm: Breaking the Barrier to Reconciling Pre/Post-Norm
Tianyu Li, Dongchen Han, Zixuan Cao +7
The long-standing tension between Pre- and Post-Norm remains an open problem in Transformer architecture, reflecting a fundamental trade-off between training stability and represen…
Eliminating Inductive Bias in Reward Models with Information-Theoretic Guidance
Zhuo Li, Pengyu Cheng, Zhechao Yu +7
Reward models (RMs) are essential in reinforcement learning from human feedback (RLHF) to align large language models (LLMs) with human values. However, RM training data is commonl…
Grounding the Score: Explicit Visual Premise Verification for Reliable Vision-Language Process Reward Models
Junxin Wang, Dai Guan, Weijie Qiu +7
Vision-language process reward models (VL-PRMs) are increasingly used to score intermediate reasoning steps and rerank candidates under test-time scaling. However, they often funct…
ATP-Bench: Towards Agentic Tool Planning for MLLM Interleaved Generation
Yinuo Liu, Zi Qian, Heng Zhou +7
Interleaved text-and-image generation represents a significant frontier for Multimodal Large Language Models (MLLMs), offering a more intuitive way to convey complex information. C…
MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination
Zhuo Li, Yupeng Zhang, Pengyu Cheng +8
Hallucination remains a critical bottleneck for large language models (LLMs), undermining their reliability in real-world applications, especially in Retrieval-Augmented Generation…
Rationale Matters: Learning Transferable Rubrics via Proxy-Guided Critique for VLM Reward Models
Weijie Qiu, Dai Guan, Junxin Wang +6
Generative reward models (GRMs) for vision-language models (VLMs) often evaluate outputs via a three-stage pipeline: rubric generation, criterion-based scoring, and a final verdict…