collaborators

5 papers

cs.CV2026

Ctrl-Z Sampling: Scaling Diffusion Sampling with Controlled Random Zigzag Explorations

Shunqi Mao, Wei Guo, Chaoyi Zhang +3

Diffusion models generate conditional samples by progressively denoising Gaussian noise, yet the denoising trajectory can stall at visually plausible but low-quality outcomes with…

cs.CL2026

Beyond Steering Vector: Flow-based Activation Steering for Inference-Time Intervention

Zehao Jin, Ruixuan Deng, Junran Wang +2

Activation steering has emerged as a promising alternative for controlling language-model behavior at inference time by modifying intermediate representations while keeping model p…

cs.AI2026

LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement Learning

Jianing Wang, Jianfei Zhang, Qi Guo +24

We introduce LongCat-Flash-Prover, a flagship 560-billion-parameter open-source Mixture-of- Experts (MoE) model that advances Native Formal Reasoning in Lean4 through agentic tool-…

cs.CL2025

EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test

Yuhui Li, Fangyun Wei, Chao Zhang +1

The sequential nature of modern LLMs makes them expensive and slow, and speculative sampling has proven to be an effective solution to this problem. Methods like EAGLE perform auto…

cs.LG2025

EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty

Yuhui Li, Fangyun Wei, Chao Zhang +1

Autoregressive decoding makes the inference of Large Language Models (LLMs) time-consuming. In this paper, we reconsider speculative sampling and derive two key observations. First…