9 papers
Reinforcement-aware Knowledge Distillation for LLM Reasoning
Zhaoyang Zhang, Shuli Jiang, Yantao Shen +6
Reinforcement learning (RL) post-training has recently driven major gains in long chain-of-thought reasoning large language models (LLMs), but the high inference cost of such model…
DLLG: Dynamic Logit-Level Gating of LLM Experts
Bingnan Li, Zhaoyang Zhang, Xiaoze Liu +6
Leveraging multiple specialized LLMs can combine complementary strengths, but existing approaches trade adaptability for stability: routing commits prematurely, heuristic ensemblin…
Talk2Move: Reinforcement Learning for Text-Instructed Object-Level Geometric Transformation in Scenes
Jing Tan, Zhaoyang Zhang, Yantao Shen +6
We introduce Talk2Move, a reinforcement learning (RL) based diffusion framework for text-instructed spatial transformation of objects within scenes. Spatially manipulating objects…
Enhancing Vision-Language Pre-training with Rich Supervisions
Yuan Gao, Kunyu Shi, Pengkai Zhu +7
We propose Strongly Supervised pre-training with ScreenShots (S4) - a novel pre-training paradigm for Vision-Language Models using data from large-scale web screenshot rendering. U…
Non-autoregressive Sequence-to-Sequence Vision-Language Models
Kunyu Shi, Qi Dong, Luis Goncalves +2
Sequence-to-sequence vision-language models are showing promise, but their applicability is limited by their inference latency due to their autoregressive way of generating predict…
Efficient Scaling of Diffusion Transformers for Text-to-Image Generation
Hao Li, Shamit Lal, Zhiheng Li +9
We empirically study the scaling properties of various Diffusion Transformers (DiTs) for text-to-image generation by performing extensive and rigorous ablations, including training…