works on

From the 1 of 25 linked papers with an AI index.

activity
20242026
collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

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…

cs.LG2025

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-…