From the 1 of 28 linked papers with an AI index.
28 papers
HSD: Hybrid Hindsight Self-Distillation
Qiye Cai, Yichuan Ma, Linyang Li +7
Reinforcement learning with verifiable rewards (RLVR) provides reliable outcome supervision for language model reasoning, but a scalar trajectory reward offers limited token-level…
AI Can Learn Scientific Taste
Jingqi Tong, Mingzhe Li, Hangcheng Li +20
The paper introduces a reinforcement‑learning framework that uses citation‑based community feedback to train models that can judge the impact of scientific papers and generate high…
Scalable Visual Pretraining for Language Intelligence
Yiming Zhang, Zhonghan Zhao, Wenwei Zhang +14
The rapid progress of large foundation models has been driven predominantly by pretraining on large-scale text corpora. However, many forms of knowledge are conveyed through visual…
Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment
Yuming Yang, Mingyoung Lai, Wanxu Zhao +13
Long chain-of-thought (CoT) trajectories provide rich supervision signals for distilling reasoning from teacher to student LLMs. However, both prior work and our experiments show t…
What Makes Position Zero Special? A Mechanistic Study of Position Zero Attention Sinks in LLMs
Runyu Peng, Ruixiao Li, Mingshu Chen +5
Transformers frequently allocate disproportionate attention to specific tokens, a phenomenon known as attention sinks. Causal large language models reliably form one at position ze…
Explicit Multi-head Attention for Inter-head Interaction in Large Language Models
Runyu Peng, Yunhua Zhou, Demin Song +4
In large language models built upon the Transformer architecture, recent studies have shown that inter-head interaction can enhance attention performance. Motivated by this, we pro…