1 citations · 1 across the 8 of their papers we have counts for
4 papers · 1 filter
Self-Confirming Superposition Traps in Reinforcement Learning
Dai Shi, Andi Han, Feng Chen +3
Reinforcement learning (RL) trains representations on data selected by the agent's policy, which then uses the resulting returns to guide its next choices. We show that this loop c…
SupportCal: Label-Free Calibration of Post-Trained LLMs via Reference Support and Corroboration
Linhan Luo, Lequan Lin, Dai Shi +3
Post-training often improves task performance but can degrade confidence calibration, leaving post-trained language models (PoLMs) more overconfident than their corresponding pretr…
FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation
Junkang Zhou, Yefei He, Feng Chen +2
Large-scale autoregressive models have demonstrated remarkable capabilities in image generation. However, their sequential raster-scan decoding relies on strictly next-token predic…
LEAD: Length-Efficient Adaptive and Dynamic Reasoning for Large Language Models
Songtao Wei, Yi Li, Zhikai Li +7
Large reasoning models, such as OpenAI o1 and DeepSeek-R1, tend to become increasingly verbose as their reasoning capabilities improve. These inflated Chain-of-Thought (CoT) trajec…