Ax Md Afif Al Mamun, Gias Uddin 7/3/2026

BLAgent: Agentic RAG for File-Level Bug Localization

LLM-based agentic RAG system for file-level bug localization in software maintenance and automated program repair.

Ax Mengdi Chu, Yang Liu, Ayan Biswas, Han-Wei Shen 7/3/2026

Do Physics Foundation Models Learn Generalizable Physics? A Bias-Aware Benchmark Across Physical Regimes and Distribution Shifts

Benchmark evaluating physics foundation models across 8 dynamics, 3 training mixtures, and 25 test regimes to assess generalization.

Ax Valentina Bui Muti, Eug\'enie Dulout, Ziquan Fu 7/3/2026

MedCase-Structured: A Text-to-FHIR Dataset for Benchmarking Diagnostic Reasoning in Clinically Realistic EHR Settings

Dataset and pipeline for benchmarking LLM diagnostic reasoning using HL7 FHIR-compliant structured EHR data from unstructured text.

Ax Qiming Shi, Zhaolu Kang, Yunfan Zhou, Di Weng, Yingcai Wu 7/3/2026

SPADER: Step-wise Peer Advantage with Diversity-Aware Exploration Rewards for Multi-Answer Question Answering

Method for multi-answer QA using tool-augmented LLM agents with peer-advantage rewards for discovering comprehensive answer sets.

Ax Hongbo Wang 7/3/2026

Exact equivariance, kept through training, buys zero-shot generalisation across the symmetry group

Theoretical analysis showing equivariant latent world models achieve zero-shot generalization across symmetry groups via invariant prediction loss.

Ax Younghun Go, Jaehoon Han, Changyong Shin, Chuck Yoo, Gyeongsik Yang 7/3/2026

Enabling KV Caching of Shared Prefix for Diffusion Language Models

Technique for KV cache optimization in diffusion language models handling bidirectional attention patterns during inference.

Ax Wanghan Xu, Shuo Li, Tianlin Ye, Qinglong Cao, Yixin Chen, Hengjian Gao, Yiheng Wang, Qi Li, Kun Li, Sheng Xu, Shengdu Chai, Fangchen Yu, Xiangyu Zhao, Zhangrui Zhao, Weijie Ma, Zijie Guo, Koutian Wu, Haoyu Zhou, Haoxiang Yin, Lixue Cheng, Chaofan Hu, Haoxuan Li, Lu Mi, Xuxuan Xie, Yifan Zhou, Ruizhe Chen, Zhiwang Zhou, Xingjian Guo, Yuhao Zhou, Xuming He, Shengyuan Xu, Xinyu Gu, Jiamin Wu, Mianxin Liu, Chunfeng Song, Fenghua Ling, Dongzhan Zhou, Shixiang Tang, Yuqiang Li, Mao Su, Peng Ye, Siqi Sun, Bin Wang, Xue Yang, Zhenfei Yin, Tianfan Fu, Guangtao Zhai, Wanli Ouyang, Bo Zhang, Lei Bai, Wenlong Zhang 7/3/2026

ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research

Benchmark for evaluating autonomous AI agents on 40 scientific research tasks across 10 domains grounded in published papers.

Ax Wesley Pang, Gregory Hyegang Jun, Feiyang Liu, Deming Chen 7/3/2026

TileFuse: A Fused Mixed-Precision Kernel Library for Efficient Quantized LLM Inference on AMD NPUs

Fused kernel library enabling efficient quantized LLM inference on AMD NPUs with mixed-precision support for on-device deployment.

Ax Liting Gao, Yonggang Zhu, Yaru Chen, Dongyu Wang, Shubin Zhang, Zhenbo Li, Jean-Yves Guillemaut, Wenwu Wang 7/3/2026

Hybrid Diffusion Transformer for Instruction-Guided Audio Editing via Rectified Flow

arXiv paper on instruction-guided audio editing using diffusion transformers with rectified flow for semantic alignment.

Ax Xiteng Yao, Taeho Kim, Hengzhi Pei, Xinle Liu, Kyle Ulrich, Leonard Lausen, Ashish Khetan, Xiang Song, George Karypis, Martin Herbordt 7/3/2026

KernelSight-LM: A Kernel-Level LLM Inference Simulator

arXiv paper presenting KernelSight-LM, a simulator for evaluating LLM inference performance across hardware and serving parameters.

Ax Shahin Hossain 7/3/2026

Four Types of LLM Reliance and Their Predictors Among Undergraduate Writers: A Mixed-Methods Study at a Minority-Serving R1 University

arXiv paper studying undergraduate reliance patterns on LLMs for academic writing. Identifies four types and predictors of LLM use.

Ax Marco Aruta, Francesco Improta, Vadim Malvone, Aniello Murano, Vladana Perli\'c 7/3/2026

Translating Natural Language to Strategic Temporal Specifications via LLMs

arXiv paper on using LLMs to translate natural language into formal temporal specifications for multi-agent systems verification.

Ax Jisung Park, Seohyeon Kang, Daeun Yoo, Eunsu Lee, Seoin Cho, Wooyeop Choi, Ian Choi, James R. Evan, Daesoo Kim, Sonia Gandhi, Minee L. Choi 7/3/2026

Resolving superposition in AI for interpretability and cross-modal alignment in patient-neuronal images

arXiv paper on resolving superposition in neural networks for biological data interpretability and cross-modal alignment in patient imaging.

Ax Ting-Bing Xu, Jiacheng Sui, Zhe Gao, Kewei Shi, Wenjin Yang, Zhicheng Liu, Zhaoxu Sun, Mingchao Sun, Hongyu Pan, Fan Jiang, Mu Xu, Qi Fan, Yang Gao, Yong Li, Baoquan Chen 7/3/2026

WorldOdysseyBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models

arXiv paper introducing WorldOdysseyBench benchmark for evaluating long-horizon stability of interactive world models across four dimensions.

Ax Enrico Cassano, Riccardo Renzulli, Rayyan Ahmed, Marco Grangetto, Stephan Alaniz 7/3/2026

Look But Don't Touch with Sparse Autoencoders for Unlearning in Diffusion Models

arXiv paper evaluating sparse autoencoders for concept manipulation and unlearning in diffusion models, focusing on object erasure.

Ax Yufei Li (Yongkang), Zaiwei Zhang (Yongkang), Mingfu Liang (Yongkang), Kavosh Asadi (Yongkang), Jay Xu (Yongkang), Jimmy Kim (Yongkang), Chongyang Bai (Yongkang), Jieyi Zhang (Yongkang), Hongye Xie (Yongkang), Prachi Agrawal (Yongkang), Dian Yu (Yongkang), Tianyi Chen (Yongkang), Jean-Pascal Billaud (Yongkang), Garret Buell (Yongkang), YK (Yongkang), Zhu (Yang), Sachin Patil (Yang), Brooke Bian (Yang), Zhou Fang (Yang), Kevin Huang (Yang), Shiva Sudanagunta (Yang), Yuzhen Huang (Yang), Emma Lu (Yang), Chris O'Brien (Yang), Yang Song (Yang), Lihong Li (Yang), Jacob Tao (Yang), Zhicheng Zhu (Yang), Chao Li (Yang), Gaoxiang Liu (Yang), Neil Wu (Yang), Li Han (Yang), Loki Chen (Yang), Ming Lei (Yang), Greg Rehm (Yang), Siyuan Song (Yang), Tianwei Zhang (Yang), Li Li (Yang), Ketan Singh (Yang), Yavuz Yetim (Yang), Ilyas Atishev (Yang), Satendra Gera (Yang), Ashkan Sadeghi (Yang), Rachel Yan (Yang), Nikko Mizutani (Yang), Shuaiwen Wang (Yang), Song Yang (Yang), Zhijing Li (Yang), Jiang Liu (Yang), Mengying Sun (Yang), Fei Tian (Yang), Xiaohan Wei (Yang), Chonglin Sun (Yang), Shuo Gu (Yang), Parish Aggarwal (Yang), Kaushik Rangadurai (Yang), Zhi Hua (Yang), Frank Shyu (Yang), Ruchit Sharma (Yang), Liyuan Li (Yang), Shike Mei (Yang), Wenlin Chen (Yang), Santanu Kolay (Yang), Ben Schulte (Yang), Deepak Chandra (Yang), Adam (Yang), Song, Sandeep Pandey, Xi Liu, Hamed Firooz, Luke Simon 7/3/2026

GR2 Technical Report

arXiv paper on using LLMs for re-ranking in industrial recommendation systems. Addresses gaps in adopting LLMs for multi-stage ranking.

Ax Soojeong Lee, Joseph Lee, Yongseong Cho, Sunjae Kim, Youngwoo Moon, Kyungwoo Song 7/3/2026

BaRA: Budget-constrained and Reliable Web Data Collection Agent

arXiv paper proposing BaRA, a budget-constrained LLM web agent for multimodal data collection with fixed interaction budgets.

Ax ZhiShu Jiang, Haibo Liu, Xin Shen, Guanqiang QI, Chenxi Miao, Weikang Li, Liwei Qian, Xin Pei, Jizhou Huang 7/3/2026

Learning User-Aware Recall: Personalized Retrieval in Long-Term Conversational Memory

arXiv paper on personalized retrieval for long-term conversational agents using profile-guided memory recall in LLM-based systems.

Ax Xiaoxiong Zhang, Xiong Zeng, Wei Zhang 7/3/2026

From World Models to World Action Models: A Concise Tutorial for Robotics

Tutorial on world models as action-conditioned predictive models for embodied AI, comparing observation-space vs state-space approaches with trade-offs.

Ax Zhishang Xiang, Zerui Chen, Yunbo Tang, Zhimin Wei, Ruqin Ning, Yujie Lin, Qinggang Zhang, Jinsong Su 7/3/2026

MemSyco-Bench: Benchmarking Sycophancy in Agent Memory

MemSyco-Bench evaluates sycophancy in LLM-agent memory systems where retrieved memories cause over-alignment with users at cost of factual accuracy.

Ax Jingwei Song, Haofeng Xu, Jie Xiao, Chengke Bao, Jingwei Shi, Pengbin Feng, Weixun Wang, Yuhang Han, Chuan Wu, Linfeng Zhang, Bill Shi 7/3/2026

Staleness-Learning Rate Scaling Laws for Asynchronous RLHF

Study of stale rollout effects in asynchronous GRPO for high-throughput RLHF, analyzing learning-rate scaling laws for decoupled policy optimization.

Ax Yuan Si, Jialu Zhang 7/3/2026

Fixed-Set Robustness in Programming by Example: Example Corruption and Semantic Partition Recovery

Study of adversarial robustness in programming-by-example systems when examples are corrupted by adversaries aware of the synthesizer.

Ax Matthew J Liu, Wei Hang Zheng, Vidhan Purohit, Siqi Xie, Chieh-En Li, Jerry Li, Noah Flynn 7/3/2026

Scaling Laws for Grid-Based Approximate Nearest Neighbor Search in High Dimensions

Scaling analysis of grid-based approximate nearest neighbor search revealing d-scaling crossover behavior on embeddings as dimensionality increases.

Ax Zhilin Zhao 7/3/2026

From Approximation to Emergence: A Theory of Deep Learning

Comprehensive theoretical book/paper unifying deep learning theory from approximation foundations through overparameterization, transformers, in-context learning, scaling laws, and emergence.

Ax Christopher Ellis, Shreyas Chaudhari, Mei-Yu Wang, Leighton Barnes, Giulia Fanti, Jos\'e M. F. Moura 7/3/2026

Black-Box Inference of LLM Architectural Properties with Restrictive API Access

Methods to infer LLM architectural properties (hidden dimensions, feed-forward layers) via black-box API access with restricted logits, studying commercial provider protections.

Ax Daniel Thi Graviet, Lovre Pesut, Ivan Dagelic, Vedran Jukic, Ivan Burazin 7/3/2026

The Rollout Infrastructure Tax in Coding-Agent Reinforcement Learning

Analysis of execution infrastructure overhead in coding-agent RL systems, measuring efficiency gains from different container/sandbox substrates for interactive rollouts.

Ax Robert Milletich, Justin Downes, Steve Goley, Newel Hirst 7/3/2026

Conditional Inference Trees and Forests for Feature Selection

Study of conditional inference trees/forests for feature selection using permutation tests, comparing computational efficiency vs ranking accuracy on benchmarks.

Ax Atsuki Yamaguchi, Szymon Palucha, L\'eo Bijar, Aline Villavicencio, Nikolaos Aletras 7/3/2026

On the Utility and Factual Reliability of Pruned Mixture-of-Experts Models in the Biomedical Domain

Evaluates factual reliability of pruned mixture-of-experts models in biomedical domain, examining trade-offs between inference speedup and accuracy.

Ax Kathan Shah 7/3/2026

Token Geometry

Ember lightweight optimizer exploits gradient geometry of embedding tables and LM-heads, improving Pareto frontier for finetuning, RL, and pretraining.

Ax Haemin Park, Diego Klabjan, Martin W. Braun, Xiuqi Li, Balakrishnan Ananthanarayanan 7/3/2026

Class-Grouped Normalized Momentum and Faster Hyperparameter Exploration to Tackle Class Imbalance in Federated Learning

FedCGNM optimizer for federated learning addresses class imbalance via class-grouped momentum and faster hyperparameter exploration.

Ax Fabian Schaipp 7/3/2026

How to Allocate Your Tokens? Scaling Laws with Training Steps and Batch Size

Three-term scaling law for LLM training explicitly modeling batch size and training steps, enabling robust fitting with fewer training runs.

Ax Juliette Decugis, Sean O'Brien, Francis Bach, Gabriel Synnaeve, Taco Cohen 7/3/2026

Don't Let Gains FADE: Breaking Down Policy Gradient Weights in RL

Framework decomposing advantage functions for RL post-training in LLMs, unifying diverse advantage formulations to address training instability.

Ax Thomas Boudou, Batiste Le Bars, Nirupam Gupta, Aur\'elien Bellet 7/3/2026

Unveiling the Non-Monotonic Effect of Privacy on Generalization under Byzantine Robustness

Shows privacy-generalization relationship in distributed learning depends on noise regime, contradicting prior Byzantine robustness trilemma results.

Ax Kevin Wang, Kevin Yang, Arjun Prakash, Amy Greenwald 7/3/2026

Towards Learning Representations of Policies in Two-Player Zero-Sum Imperfect-Information Games

Methods for creating policy datasets and learning policy embeddings in two-player zero-sum imperfect-information games with evaluation tasks.

Ax Lukas Haverbeck, Carmen Amo Alonso, Andres Felipe Posada-Moreno, Sebastian Trimpe, Marco Pavone 7/3/2026

The risk of KV cache compression

Theoretical analysis of KV cache compression in transformer inference showing when compression is impossible and deriving fundamental limits.

Ax Jiatong Li, Samuel Yeh, Sharon Li 7/3/2026

Multi-Head Recurrent Memory Agents

Multi-Head Recurrent Memory Agents diagnose reliability degradation in long-context LLMs, attributing failures to memory retention rather than capture.

Ax Ege Onur Taga, Yilin Zhuang, M. Emrullah Ildiz, Petros Mol, Abhimanyu Das, Karthik Duraisamy, Samet Oymak 7/3/2026

Evolutionary Feature Engineering for Structured Data

EFE framework uses LLM-based evolutionary optimization to discover preprocessing transformations for structured data as Python programs.

Ax Leyan Li, Rennong Yang, Zhenxing Zhang, Liping Hu 7/3/2026

X-LogSMask: Expand Transformer for Graph-Structured Data

X-LogSMask modifies transformer architecture with explainable multi-head attention for improved performance on sparse, structured graph data.

Ax Aria Masoomi, Mahsa Bazzaz, Adel Javanmard, Vahab Mirrokni 7/3/2026

Geometric Signatures of Reasoning: A Spectral Perspective on Task Hardness

Studies geometric properties of chain-of-thought reasoning trajectories in transformer hidden states to understand task difficulty and reasoning mechanisms.

Ax Zewen Liu 7/3/2026

BOUNDARY_SYNC: Measuring Communication-Induced Representational Coupling in Multi-Agent LLM Systems

BOUNDARY_SYNC measures representational coupling in multi-agent LLM systems, quantifying how inter-agent communication causes convergence or divergence.

Ax Saoud Aldowaish, Yashwanth Karumanchi, Kai-Chen Chiang, Mohammed Ayman Habib, Finn Murphy, Rishen Cao, Morteza Fayazi 7/3/2026

SINA: A Fully Automated Circuit Schematic Image to Netlist Generator Using Artificial Intelligence

SINA uses AI to convert circuit schematic images to machine-readable netlists for electronic design automation tasks.

Ax Haotian Xie, Junlin Chen, Mingkai Zheng, Lishan Yang, Zhao Zhang 7/3/2026

DeadPool: Resilient LLM Training with Hot-Swapping via Zero-Overhead Checkpoint

DeadPool enables resilient LLM training at scale by implementing hot-swapping with zero-overhead checkpointing for GPU failure recovery.

Ax Mingkai Zheng, Junlin Chen, Haotian Xie, Zhao Zhang 7/3/2026

SCAPE: Accurate and Efficient LLM Training with Extreme Sparse Communication

Communication-efficient LLM training via extreme sparse gradient synchronization with stable sparse Adam optimizer.

Ax Tzu-Heng Huang, Aditya Goyal, John Cooper, Frederic Sala 7/3/2026

WARP: Weight-Space Analysis for Recovering Training Data Portfolios

Method for inferring training data mixture weights and source distributions from released foundation models.

Ax Long Minh Bui, Tuan Anh Le Van, Tung Phi Duc, Phi Le Nguyen, Jana Doppa, Trong Nghia Hoang 7/3/2026

Model Merging as Probabilistic Inference in Fine-Tuning Parameter Space

Probabilistic inference framework for merging task-specific fine-tuned models into multi-task solutions.

Ax Jianfeng Lu 7/3/2026

A Mathematical Introduction to Diffusion Models

Mathematical introduction to diffusion models covering sampling dynamics, error analysis, and inference-time control.

Ax Xiong Xiong, Ruonan Zhai, Zheng Zeng, Sheng Zhou, Rongchun Hu, Zichen Deng 7/3/2026

Frequency Shift Physics-Informed Extreme Learning Machine for Solving High-Frequency Partial Differential Equations

Physics-informed extreme learning machine addressing spectral bias for solving high-frequency PDEs.

Ax Nikolai Smolyanskiy 7/3/2026

Predicting Closed-Loop Performance of Latent World Models: Offline Checkpoint Selection for MPC and Model-Based RL Under Non-Markovian Rewards in LunarLander

Validation diagnostics for selecting optimal checkpoints of latent world models in model predictive control and model-based RL.

Ax He Huang, Lu Shen, Yunfeng Huang, Li Qi 7/3/2026

Role-Aware Neural Convex Divergence Heads for Asymmetric Representation Learning

Neural divergence heads for asymmetric representation learning in directed relational tasks.

Ax Meng Wang, Haohan Zhao, Wenzhuo Liu, Lu Yang, Geng Liu, Haiyang Guo, Guo-Sen Xie, Gaofeng Meng, Hongbin Liu, Fei Zhu 7/3/2026

Denser $\neq$ Better: Limits of On-Policy Self-Distillation for Continual Post-Training

Analysis of self-distillation for continual post-training showing trade-offs between in-domain specialization and knowledge preservation.