From the 1 of 25 linked papers with an AI index.
6 papers · 1 filter
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…
When Do LLMs Reason? A Dynamical Systems View via Entropy Phase Transitions
Wei Xia, Haoqing Wang, Zhi-Hong Deng +1
Chain-of-thought (CoT) reasoning has become the default strategy for enhancing LLM capabilities, yet its application raises a fundamental question: when is explicit reasoning actua…
Gated KalmaNet: A Fading Memory Layer Through Test-Time Ridge Regression
Liangzu Peng, Aditya Chattopadhyay, Luca Zancato +3
Linear State-Space Models (SSMs) offer an efficient alternative to softmax Attention with constant memory and linear compute, but their lossy, fading summary of the past hurts reca…
Priming: Hybrid State Space Models From Pre-trained Transformers
Aditya Chattopadhyay, Elvis Nunez, Prannay Kaul +6
Hybrid State-Space models combine Attention with recurrent State-Space Model (SSM) layers, balancing eidetic memory from Attention with compressed fading memory from SSMs. This yie…
Experience Sharing in Mutual Reinforcement Learning for Heterogeneous Language Models
Xiaoze Liu, Dhananjay Ram, Yuting Zhang +3
We introduce Mutual Reinforcement Learning, a framework for concurrent RL post-training in which heterogeneous LLM policies exchange typed experience while keeping separate paramet…
Beyond Hidden-Layer Manipulation: Semantically-Aware Logit Interventions for Debiasing LLMs
Wei Xia
We proposed Static and Dynamic -- two zero-shot logits-layer debiasing methods. Dynamic reduces bias by up to 70% with minimal fluency loss. Logits intervention outperforms hidden-…