6 papers
Beyond Binary: Turning Partial Success into Dense Verifiable Rewards for Reinforcement Learning in Code Generation
Longwen Wang, Yirui Liu, Xuan'er Wu +6
Effective reward design is a central challenge in Reinforcement Learning (RL) for code generation. Mainstream test-suite-level outcome rewards enforce functional correctness but in…
Awakening Dormant Experts:Counterfactual Routing to Mitigate MoE Hallucinations
Wentao Hu, Yanbo Zhai, Xiaohui Hu +6
Sparse Mixture-of-Experts (MoE) models have achieved remarkable scalability, yet they remain vulnerable to hallucinations, particularly when processing long-tail knowledge. We iden…
Reward-Aware Trajectory Shaping for Few-step Visual Generation
Rui Li, Bingyu Li, Yuanzhi Liang +3
Achieving high-fidelity generation in extremely few sampling steps has long been a central goal of generative modeling. Existing approaches largely rely on distillation-based frame…
HSSBench: Benchmarking Humanities and Social Sciences Ability for Multimodal Large Language Models
Zhaolu Kang, Junhao Gong, Jiaxu Yan +15
Multimodal Large Language Models (MLLMs) have demonstrated significant potential to advance a broad range of domains. However, current benchmarks for evaluating MLLMs primarily emp…
RecTok: Reconstruction Distillation along Rectified Flow
Qingyu Shi, Size Wu, Jinbin Bai +5
Visual tokenizers play a crucial role in diffusion models. The dimensionality of latent space governs both reconstruction fidelity and the semantic expressiveness of the latent fea…
Improve LLM-as-a-Judge Ability as a General Ability
Jiachen Yu, Shaoning Sun, Xiaohui Hu +3
LLM-as-a-Judge leverages the generative and reasoning capabilities of large language models (LLMs) to evaluate LLM responses across diverse scenarios, providing accurate preference…