17 papers
LC-ERD: Mining Latent Logic for Self-Evolving Reasoning via Consistency-Regulated Reward Decomposition
Yanyu Chen, Jiyue Jiang, Dianzhi Yu +8
The evolution of Large Language Model (LLM) reasoning is bottlenecked by the scarcity of high-quality process data. While self-alignment via endogenous rewards offers a solution, m…
BitLM: Unlocking Multi-Token Language Generation with Bitwise Continuous Diffusion
Shaobin Zhuang, Yuang Ai, Jiaming Han +7
Autoregressive language models generate text one token at a time, yet natural language is inherently structured in multi-token units, including phrases, n-grams, and collocations t…
Auto-Rubric as Reward: From Implicit Preferences to Explicit Multimodal Generative Criteria
Juanxi Tian, Fengyuan Liu, Jiaming Han +6
Aligning multimodal generative models with human preferences demands reward signals that respect the compositional, multi-dimensional structure of human judgment. Prevailing RLHF a…
OpenGame: Open Agentic Coding for Games
Yilei Jiang, Jinyuan Hu, Qianyin Xiao +8
Game development sits at the intersection of creative design and intricate software engineering, demanding the joint orchestration of game engines, real-time loops, and tightly cou…
GIDE: Unlocking Diffusion LLMs for Precise Training-Free Image Editing
Zifeng Zhu, Jiaming Han, Jiaxiang Zhao +2
While Diffusion Large Language Models (DLLMs) have demonstrated remarkable capabilities in multi-modal generation, performing precise, training-free image editing remains an open c…
Cubic Discrete Diffusion: Discrete Visual Generation on High-Dimensional Representation Tokens
Yuqing Wang, Chuofan Ma, Zhijie Lin +7
Visual generation with discrete tokens has gained significant attention as it enables a unified token prediction paradigm shared with language models, promising seamless multimodal…