| 1 | Graph Machine: Towards Better Pretraining via Edges | Lintai Hou | cs.LG | 2026-09-02 |
| 2 | RoGe: Novel View Synthesis via End-to-End Implicit Reconstruction and Generation | Xiaolei Lang, Ze Kang, Zehao Huang +1 | cs.CV | 2026-09-02 |
| 3 | UE5M3 FP4 Block Scaling for Stable Language Model Pretraining | Robert Hu, Carlo Luschi, Paul Balanca | cs.LG | 2026-09-02 |
| #4 | Cliff: Learning Process Rewards from the First Mistake | Peixuan Han, Runhui Wang, Ketan Ramaneti +3 | cs.LG | 2026-09-02 |
| #5 | EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction | Yuling Shi, Zhensu Sun, Junsen Dong +3 | cs.CL | 2026-09-02 |
| #6 | ShallowStream: Index Shallow then Answer Deep for Streaming Video Understanding | Jitai Hao, Ke Yang, Qiang Huang +1 | cs.CV | 2026-09-02 |
| #7 | Language Models Can Control Their Own Attention | Namgyu Ho, Huzama Ahmad, Woosung Koh +3 | cs.CL | 2026-09-02 |
| #8 | RVSD: Retrieval Vision Sparse Decoding for Mitigating Visual Hallucinations in Large Vision-Language Models | Canjie Liu, Jiawen Kang, Jinbo Wen +1 | cs.CV | 2026-09-02 |
| #9 | From Tokens to Semantics: Leveraging Complementary Signals for Hallucination Detection in Black-Box LLMs | Urja Pawar, Rajitha Ramanayake, Owen O'Neill +4 | cs.CL | 2026-09-02 |
| #10 | MARS: What Retrieval Signals Are Hidden in Multimodal Large Language Models for Text-Video Retrieval? | Uicheol Jung, Juyoung Hong, Geuntaek Lim +1 | cs.CV | 2026-09-02 |
| #11 | Spatially Aware World Action Model via Geometric Latent Diffusion | Javier Alejandro Lopetegui Gonzalez, Paul Pacaud, Cordelia Schmid | cs.CV | 2026-09-02 |
| #12 | Evidence for Shared Routing Geometry and Dynamics in Sparse Mixture-of-Experts | Kirill Labzin, Stepan Kulibaba, Artem Dzhalilov +1 | cs.LG | 2026-09-02 |
| #13 | CA-OPD: Confidence-Aware On-Policy Distillation for Structured Visual Prediction | Menghao Li, Linjie Mu, Yin Wang +4 | cs.CV | 2026-09-02 |
| #14 | ProSR: Semantic-Prototype-Guided Discrete Modeling for Physically Consistent SAR Super-Resolution | Byoungwoo Kim, Munchurl Kim | cs.CV | 2026-09-02 |
| #15 | TempoGround: State-Aware Streaming Visual Grounding with Vision-Language Models | Leqian Ding, Junning Qiu, Manwen Yang +2 | cs.CV | 2026-09-02 |
| #16 | DiffIE: Diffusion-based Open Information Extraction | Konstantin Fedorov, Valentin Malykh | cs.CL | 2026-09-02 |
| #17 | SEAL: Reinforcing Global Safety in Mixture-of-Experts through Shared Expert ALignment | Qingyu Meng, Yiwei Zha, Jiahuan Pei +3 | cs.LG | 2026-09-02 |
| #18 | SCX Router: Streaming Zero-Shot Model Selection with a Decoder-KV Classifier and a Real-World Task Ontology | Ihor Stepanov, Aleksandr Smechov, Mykhailo Shtopko +2 | cs.AI | 2026-09-02 |
| #19 | Codebook Agent: Amortized Topology Design for LLM Multi-Agent Systems | Jinxi Yu, Yubei Li, Eric Hanchen Jiang +6 | cs.AI | 2026-09-02 |
| #20 | TAME: Temporal-Aware Mixture-of-Experts for Text-Video Retrieval | Uicheol Jung, Juyoung Hong, Hojung Kwon +1 | cs.CV | 2026-09-02 |
| #21 | WeaveMark: Robust and Scalable Multi-bit LLM Watermarking via Coded Payload Spreading | Gang-Hyun Park, Ju-Hyeong Lee, Hee-Youl Kwak +1 | cs.CR | 2026-09-02 |
| #22 | A Unified Rate-Distortion Perspective on Vector, Product, and Scalar Quantization | Xianghong Fang, Wenlong Mou, Yuan Yuan +2 | cs.LG | 2026-09-02 |
| #23 | XMerge: Cross-Axis Selection and Reconstructive Layer Merging for LLM Depth Compression | Jundong Hu, Shekar Ramachandran | cs.LG | 2026-09-02 |
| #24 | Monitoring Web Agents Without Internal Signals: Observable Trajectories and Key-Step Supervision | Sitong Pan, Yipeng Shen, Yilin Lu +3 | cs.AI | 2026-09-02 |
| #25 | The Dynamics of Continuous Mixture Collapse in Language Models | Ali Backour | cs.LG | 2026-09-02 |
| #26 | GeoStore: Finding Small Storefronts in Large Scenes -- A Fine-Grained POI Localization Benchmark with Global-to-Local Asymmetric Matching | Lu Han, Xiting Sun, Hao Wang +4 | cs.CV | 2026-09-02 |
| #27 | Seed-Anchored Budget-Bounded Graph Rendering for Question Answering on Industry-Standard Power-Grid Information and Exchange Models | Jayakumar Manoharan, Yamini Sehgal | eess.SY | 2026-09-02 |
| #28 | Train What You Deploy: Closing the MLP Reachability Gap in Low-Rank Clone Distillation | Wenhui Chen, Zhifeng Li, Jie Zhou +5 | cs.LG | 2026-09-02 |
| #29 | Sparse Readout Prism: Explaining Logit-Lens Scores in Features Instead of Tokens | Matteo He, William F. Shen, Xinchi Qiu +1 | cs.CL | 2026-09-01 |
| #30 | CRISP: Cliff-awaRe Input-adaptive Sparse Prefilling with Structural-Mass-Motivated Routing | Huu Huy Nguyen, Chien Van Nguyen, Franck Dernoncourt +4 | cs.LG | 2026-09-01 |
| #31 | GAPS: Dimension-Level Gates for Conditional Activation Steering | Moghis Fereidouni, Muhammad Umair Haider, Hassan Sajjad +1 | cs.CL | 2026-09-01 |
| #32 | hLLM: Single Pass Decoding for Generative Reranking | Emil Laftchiev, Prachi Agrawal, Moe Kayali +7 | cs.LG | 2026-09-01 |
| #33 | How Do Prompt Variations Affect Energy Consumption in On-Device LLMs? | Wei Hu, Xiaolong Tu, Dawei Chen +3 | cs.CL | 2026-09-01 |
| #34 | Dictionary-Guided Mutation Operators for Automated HDL Repair | Maisha Mastora, Dean Sullivan | cs.ET | 2026-09-01 |
| #35 | ZipTok3D: High-Fidelity 3D Tokenization with Compact Token Prefixes | Mingda Lin, Weijie Wang, Zeyu Zhang +7 | cs.CV | 2026-09-01 |
| #36 | Beyond Scores: Understanding LLM-as-a-Judge Mechanisms in Summarization Evaluation | Himil Vasava, Ming Jiang | cs.CL | 2026-09-01 |
| #37 | Adaptive Critical Token-Aware Retrieval for Repository-Level Code Generation | Kefeng Duan, Dewu Zheng, Yanlin Wang +8 | cs.SE | 2026-09-01 |
| #38 | CordisBench: Can Language Models Reason About Component Lifecycles in Dynamic Agent Harnesses? | Damien Sileo, Dimitri Kachler | cs.CL | 2026-09-01 |
| #39 | Retrieved but not ranked: surface-form bias in structural retrieval, from mathematics to agent trajectories | Nabira Rashid, Manolis Kellis | cs.LG | 2026-09-01 |
| #40 | Knowledge Distillation During Mid-Training Favors Reasoning over Factual Recall | Jacqueline He, Howard Yen, Shuyue Stella Li +9 | cs.CL | 2026-09-01 |
| #41 | LatentPress: Context Compression Beyond Text and Vision | Zhengze Zhou, Hejian Sang | cs.LG | 2026-09-01 |
| #42 | Parsing the Stream: A Live Trace Model for Long-Horizon Agents and Their Observers | Egor Pakhomov, Erik Nijkamp | cs.AI | 2026-09-01 |
| #43 | HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness? | Yuhao Wu, Jingyuan Zhang, Jiajun Shi +16 | cs.SE | 2026-09-01 |
| #44 | TRIAGE: Three-level Routing and Intelligent Agent Guidance for Efficient Execution | Ruocan Wei | cs.LG | 2026-09-01 |
| #45 | When Tokenization is Secretly Output Supervision | Tanja Baeumel, Josef van Genabith, Simon Ostermann | cs.CL | 2026-09-01 |
| #46 | Learning Evidence Sufficiency Boundaries for Selective Answering in Grounded Multi-Hop QA | Haruto Sato, Yuki Tanaka, Ren Nakamura +2 | cs.CL | 2026-09-01 |
| #47 | Polish ModernBERT: The Long and Short of Polish Language Understanding | Michał Perełkiewicz, Sławomir Dadas, Rafał Poświata +1 | cs.CL | 2026-09-01 |
| #48 | SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers | Shaowen Wang, Ge Zhang, Kairong Luo +6 | cs.LG | 2026-09-01 |
| #49 | mzCache: On-Device LLM Memory Management under Multitasking | Hongseung Yu, Minsung Kim, Jongseok Park +1 | cs.OS | 2026-09-01 |
| #50 | Reliability Challenges in Diffusion Vision-Language Models | Md. Atabuzzaman, Chris Thomas | cs.CV | 2026-09-01 |