activity
20242026
collaborators

7 papers

cs.AI2026

Controlling Exploration-Exploitation in GFlowNets via Markov Chain Perspectives

Lin Chen, Samuel Drapeau, Fanghao Shao +5

Generative Flow Network (GFlowNet) objectives implicitly fix an equal mixing of forward and backward policies, potentially constraining the exploration-exploitation trade-off durin…

cs.LG2026

Towards Compressive and Scalable Recurrent Memory

Yunchong Song, Jushi Kai, Liming Lu +2

Transformers face a quadratic bottleneck in attention when scaling to long contexts. Recent approaches introduce recurrent memory to extend context beyond the current window, yet t…

cs.AI2026

Flow of Spans: Generalizing Language Models to Dynamic Span-Vocabulary via GFlowNets

Bo Xue, Yunchong Song, Fanghao Shao +5

Standard autoregressive language models generate text token-by-token from a fixed vocabulary, inducing a tree-structured state space when viewing token sampling as an action, which…

cs.CL2026

Next Concept Prediction in Discrete Latent Space Leads to Stronger Language Models

Yuliang Liu, Yunchong Song, Yixuan Wang +6

We propose Next Concept Prediction (NCP), a generative pretraining paradigm built on top of Next Token Prediction (NTP). NCP predicts discrete concepts that span multiple tokens, t…

cs.CL2026

FLAME: Empowering Frozen LLMs for Knowledge Graph Completion

Bo Xue, Yi Xu, Bolei Ma +4

Traditional knowledge graph completion (KGC) methods rely solely on structural information and struggle with sparsity, while Large Language Models (LLMs) address these limitations…

cs.LG2025

FlowRL: Matching Reward Distributions for LLM Reasoning

Xuekai Zhu, Daixuan Cheng, Dinghuai Zhang +20

We propose FlowRL: matching the full reward distribution via flow balancing instead of maximizing rewards in large language model (LLM) reinforcement learning (RL). Recent advanced…