arXiv AI

When Should Graph Attention Be Sparse? Learning a Per-Edge Tsallis Index

arXiv:2608. 02938v1 Announce Type: cross Abstract: Graph attention normalizes neighborhood scores with softmax, the maximum-entropy choice under Shannon statistics.

arXiv Machine Learning

Jul 10

Uncertainty-gated selection for block-sparse attention

arXiv:2607. 07724v1 Announce Type: new Abstract: Block-sparse attention scales long-context language models by replacing the O(N^2) softmax with a per-query top-k selection over key blocks.

By Thomas Rossi

llms

arXiv AI

Jun 12

MiniMax Sparse Attention

arXiv:2606. 13392v1 Announce Type: new Abstract: Ultra-long-context capability is becoming indispensable for frontier LLMs: agentic workflows, repository-scale code reasoning, and persistent memory all require the model to jointly attend over hundreds of thousands to millions of tokens, yet the quadratic cost of softmax attention makes this untenable at deployment scale.

By Xunhao Lai, Weiqi Xu, Yufeng Yang, Qiaorui Chen, Yang Xu, Lunbin Zeng, Xiaolong Li, Haohai Sun, Haichao Zhu, Vito Zhang, Pengyu Zhao

llms agents efficiency multimodal

arXiv Machine Learning

Jun 3

Pruning Deep Neural Networks via the Marchenko--Pastur Distribution

arXiv:2606. 02608v1 Announce Type: new Abstract: We study a Marchenko--Pastur (MP) random-matrix approach to pruning deep neural networks with very small post-pruning fine-tuning budgets.

By Leonid Berlyand, Theo Bourdais, Houman Owhad, Yitzchak Shmalo

fine-tuning efficiency

arXiv AI

Aug 13

Rubric Dropout: A Simple Way to Mitigate Reward Hacking in Rubric-as-Reward RL

arXiv:2608. 11669v1 Announce Type: cross Abstract: Reinforcement learning against rubrics, lists of criteria graded by an LLM judge, has become a standard way to post-train language models on tasks with no deterministic answer.

By Minglai Yang, Xinyu Guo, Utkarsh Tyagi, Mian Zhang, Razvan Dumitru, Sunjie Hou, Yunzhong He, Daniel Yue Zhang, Ying Liu

llms reinforcement-learning benchmarks safety

arXiv AI

Jun 2

UR-JEPA: Uniform Rectifiability as a Regularizer for Joint-Embedding Predictive Architectures

arXiv:2606. 01443v1 Announce Type: cross Abstract: A central difficulty in training Joint-Embedding Predictive Architectures (JEPAs) is preventing representation collapse.

By Triet M. Le

rag

arXiv AI

Jun 9

Capacity-Controlled Global Attention for Graph Transformers

arXiv:2604. 17324v2 Announce Type: replace-cross Abstract: Global self-attention drives modern graph transformers, yet the softmax at its core imposes a structural constraint rarely examined directly: every attention row is non-negative and sums to one, so each per-head output is a mass-conserving convex combination of value vectors.

By Yang Liu, Dongxin Guo, Tom Zheng, Siu Ming Yiu, Liam Ning, Jikun Wu

llms benchmarks

arXiv Machine Learning

Jun 30

Depth-Staggered Fibonacci Spacing for Sparse Attention: Static Schedules Beat Learned Dilation and Extrapolate Where Dense Attention Fails

arXiv:2606. 28560v1 Announce Type: cross Abstract: We study sparse self-attention in which each query attends to a dense local window plus a set of Fibonacci-spaced offsets, with a per-layer scalar alpha that compresses or expands the spacing.

By Chad A. Capps

llms efficiency

arXiv Machine Learning

Aug 11

Quality-Diversity Stress Tests for Process Reward Models:What Archive Coverage Can and Cannot Certify

arXiv:2608. 08008v1 Announce Type: new Abstract: Process reward models (PRMs) score intermediate reasoning steps and are widely used for search, ranking, and training, but optimization can exploit these learned proxies by increasing reward while turning correct reasoning into incorrect reasoning.

By Ibne Farabi Shihab, Fariya Afrin

fine-tuning safety

Hugging Face Trending Papers

Jul 20

MADA-RL: Multi-Agent Debate-Aware Reinforcement Learning for Parameter-Efficient Reasoning in Compact Models

Large language models achieve strong reasoning performance, but often at prohibitive training cost - a challenge that is especially acute for compact models ($\leq 4 \, \mathrm{B}$ parameters) trained under limited budgets. We introduce MADA-RL, a post-training framework that specializes compact models into generator and critic roles and trains them with a debate-aware learning signal, fine-tuning only a small subset of parameters via LoRA adapters.

llms agents reinforcement-learning fine-tuning benchmarks

arXiv AI

Jul 21

MADA-RL: Multi-Agent Debate-Aware Reinforcement Learning for Parameter-Efficient Reasoning in Compact Models

arXiv:2607. 18006v1 Announce Type: cross Abstract: Large language models achieve strong reasoning performance, but often at prohibitive training cost - a challenge that is especially acute for compact models ($\leq 4 \, \mathrm{B}$ parameters) trained under limited budgets.

By Martino M. L. Pulici, Cuong Xuan Chu, Evgeny Kharlamov, Zifeng Ding, Volker Tresp, Yunpu Ma

llms agents reinforcement-learning fine-tuning benchmarks

arXiv Machine Learning

Jul 14

Rank-Conditioned Sample Reuse for the Plackett--Luce Best-of-$K$ Objective

arXiv:2607. 11146v1 Announce Type: new Abstract: We study the coupled objective J_K^WOR = E_{S ~ PL-WOR_K}[max_{i in S} R_i]: the expected maximum reward of a size-K Plackett-Luce draw without replacement, the law of Gumbel-Top-K / Stochastic Beam Search decoding.

By Melveena Jolly, Midhun Xavier

arXiv Machine Learning

Aug 5

ATFlash: Per-RoPE-Wavelength Attention Windows for Compute/Memory-Efficient LLM Inference

arXiv:2608. 02947v1 Announce Type: new Abstract: The attention score with rotary position embeddings (RoPE) decomposes exactly into a sum over its 2D-rotation frequency pairs, and each pair's wavelength limits how far it can discriminate position.

By Shun-ichiro Hayashi, Daichi Mukunoki, Tetsuya Hoshino, Takahiro Katagiri

llms rag efficiency benchmarks

Related stories