9 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…
Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model
Qingyu Shi, Jinbin Bai, Zhuoran Zhao +7
Unified generation models aim to handle diverse tasks across modalities -- such as text generation, image generation, and vision-language reasoning -- within a single architecture…
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…
Personalized Safety Alignment for Text-to-Image Diffusion Models
Yu Lei, Jinbin Bai, Qingyu Shi +4
Text-to-image diffusion models have revolutionized visual content generation, yet their deployment is hindered by a fundamental limitation: safety mechanisms enforce rigid, uniform…
Training Report of TeleChat3-MoE
Xinzhang Liu, Chao Wang, Zhihao Yang +51
TeleChat3-MoE is the latest series of TeleChat large language models, featuring a Mixture-of-Experts (MoE) architecture with parameter counts ranging from 105 billion to over one t…
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…