| 1 | Augustinian BabyLM: What Ostensive Definition Can and Cannot Teach a Small Language Model | Lisa Bylinina | cs.CL | 2026-09-10 |
| 2 | The widening evaluation gap in medical large language model research 2023 to 2026 | Raad Bin Tareaf, Murad Al-Rajab, Samia Loucif | cs.CL | 2026-09-10 |
| 3 | A Unified Per-Token Gating Family for On-Policy Distillation: FKL/RKL Mixing with Multi-Channel and Bias Coefficients | Suwan Wu, Yumeng Lin, Pengcheng Yuan +1 | cs.AI | 2026-09-10 |
| #4 | The Eloquence submission for Task 2 of the Interspeech 2026 MLC-SLM challenge | Jordi Luque, Lorenzo Concina, Marco Matassoni +2 | cs.CL | 2026-09-10 |
| #5 | A Dataset and Model for Imputing Water Surface Elevation on a Large and Extremely Sparse Spatiotemporal Graph | Ruben Cartuyvels, Karim Douch, Gabriele Bertoli +4 | cs.LG | 2026-09-10 |
| #6 | Pre- and Post-Treatment Brain Metastases Segmentation Using nnU-Net with Post-Processing for BraTS 2026 | Haobin Liu, Xin Wang | cs.CV | 2026-09-10 |
| #7 | Magenta: Closing the Loop Between Mathematical Reasoning and Lean Verification | Joshua Ong Jun Leang, Haonan Li, Zheng Zhao +6 | cs.AI | 2026-09-10 |
| #8 | HALDETECT at ImageEval 2026 Shared Tasks: Answer-First Contrastive Grounding with QLoRA | Syed Mohaiminul Hoque, Md Sakhawat Hossain | cs.CV | 2026-09-10 |
| #9 | A Multi-View and Confusion-Guided Ensemble Framework for Robust Synthetic Image Attribution | Zuomin Qu | cs.CV | 2026-09-10 |
| #10 | Overview of the NLPCC 2026 Shared Task 11: Agent-Based Experiment Reproduction from Scientific Papers | Hanhua Hong, Yizhi Li, Luu Gia Huy +3 | cs.CL | 2026-09-10 |
| #11 | Fork Where the Model Changes Its Mind: Belief-Shift Branching for Tree-Structured Reinforcement Learning | Bin Lei, Yu Li, Prafulla Kumar Choubey +7 | cs.AI | 2026-09-10 |
| #12 | Relatively Smart II: Tractable or Semi-Supervised Instance-Optimal Learning | Shaddin Dughmi, Alireza F. Pour | cs.LG | 2026-09-09 |
| #13 | DR-LabStack: Design and Implementation of a Clinician-Facing Web System for Diabetic Retinopathy Prediction | Yingfan Xu, Tieming Liu, Ye Liang | cs.LG | 2026-09-09 |
| #14 | An Open Recipe for IMO Gold: Training Nemotron for Olympiad Mathematics | Ivan Moshkov, Stephen Ge, George Armstrong +3 | cs.AI | 2026-09-09 |
| #15 | Data-Efficient Language Modeling: From Frontier Advancement to Principle-Guided Model Improvement | Shuxing Yang, Kaihao Zhu, Junjie Yang +13 | cs.CL | 2026-09-09 |
| #16 | More than half of recent astronomy papers are written with language-model assistance | Serat M. Saad, Yuan-Sen Ting | astro-ph.IM | 2026-09-09 |
| #17 | Rosetta at AlexandriaX-2026: LoRA-Adapted NileChat for Context-Aware Dialectal Arabic Dialogue Translation | Nada Esmaeil, Fathima Rena, Sibi Subhash +4 | cs.CL | 2026-09-09 |
| #18 | Two-Token Features and Small-Large Ensembles for VLM Hallucination Detection | Eli Schwartz | cs.CL | 2026-09-09 |
| #19 | 3rd Place Solution to Human Motion Challenges in Real-World and Clinical Settings (MoCha) @ECCV2026: Language-Aligned Motion Representations for Domain-Generalizable UPDRS-Gait Severity Estimation | Soojie Kim, Muhammad Munsif, Minkyung Kim +1 | cs.CV | 2026-09-09 |
| #20 | SalamandraTA at WMT 2026 Terminology Shared Task: Hard Examples Are Better Teachers | Xixian Liao, Maite Melero | cs.CL | 2026-09-09 |
| #21 | MUCnoHARM@GermEval Shared Task 2026: Retrieval-based In-Context Learning for Defamatory Offences, and Where It Falls Short | Kristin Gnadt, Maximilian Meidinger, Matthias Aßenmacher | cs.CL | 2026-09-09 |
| #22 | EEGBind: Detecting Source-Level Interictal Epileptiform Discharges via EEG-Centric Multimodal Binding | Muchen Li, Anglin Liu, Xuetian Gao +2 | cs.LG | 2026-09-09 |
| #23 | Looped GPT-BERT: Trading Parameters for Computation in Small Language Modeling | Tingshuo Fan, Hongtao Mu, Tianyu Zhou +2 | cs.CL | 2026-09-09 |
| #24 | Seven Sources of Physical AI Capability Formation | Gang Chen | cs.AI | 2026-09-09 |
| #25 | Watermarks Without Verification: AI Text Watermarking After the EU AI Act | Alexander Nemecek, Vipin Chaudhary, Erman Ayday | cs.CY | 2026-09-09 |
| #26 | Copying explains the collective behavior of AI agents in the wild | Giordano De Marzo, Nicola Alboré, David Garcia | cs.MA | 2026-09-08 |
| #27 | GoAnt: Quality-Diversity Multi-Agent Search for Alpha Factor Discovery in Market Microstructure Data | Stella Zhao, Tommy Sha | cs.AI | 2026-09-08 |
| #28 | TontaubeV1: Streaming Text-to-Speech with Hierarchical Codec Modeling and Bounded Context | Fritz Cremer, Jonathan Cremer | cs.SD | 2026-09-08 |
| #29 | GOLF: Global Observation with Local Focus for Calibration-Aware Stereo Interaction Field Estimation | Minqiang Zou, Riqiang Jin, Zhi Lv +7 | cs.CV | 2026-09-08 |
| #30 | Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models | Zongjie Li, Alan Z. W, John Nicolas J +4 | cs.AI | 2026-09-08 |
| #31 | SoftRerank: Hierarchical Soft Fusion with Candidate-Label Reranking for Long-Tailed Micro-Action Recognition | Yichi Zhang, Zhichao Xia, Yanjun Chi +6 | cs.CV | 2026-09-08 |
| #32 | Snugi-AI-v2 @ eRisk 2026 Task 2: Early Depression Detection via a Learned Stopping Policy with Sustained Confidence Gate | Yuwen Chiu | cs.CL | 2026-09-08 |
| #33 | IGT @ FinMMEval 2026 Task 2: Question-Type Prompting with Targeted Extraction for Multilingual Financial QA | Yuwen Chiu | cs.CL | 2026-09-08 |
| #34 | RFS-UNet: Decoder-Conditioned High-Resolution Skip Recalibration for Bone-Selective DRR Synthesis | Xiaoyang Li, Yixuan Liu, Yuan Chai | cs.CV | 2026-09-07 |
| #35 | Sharp Structure-Agnostic Minimax Risk for Partial Linear Models | Haichen Hu, David Simchi-Levi | cs.LG | 2026-09-07 |
| #36 | Solution for UCF UrbanTwin LUMPI Track: Sim-to-Real Urban LiDAR 3D Object Detection | Pu Luo, Cong Xu, Yumei Li +4 | cs.CV | 2026-09-07 |
| #37 | An LLM-Associated Register Shift in Korean Journal Abstracts: A Morphology-Aware Excess-Vocabulary Study, 2018-2026 | Aron Lee | cs.CL | 2026-09-07 |
| #38 | REFINE: Trajectory Representation Learning via Closed-Loop Transcription -- Extended Version | Sean Bin Yang, Ying Sun, Jilin Hu +5 | cs.LG | 2026-09-07 |
| #39 | Ambient @ EgoLongQA 2026: Distilling Long-Video perception into a Sub-2B Model | Logesh Kumar Umapathi | cs.CV | 2026-09-07 |
| #40 | Retrieval-Augmented Multi-Prompt Ensemble for Minor-Grain Breeding Information Extraction | Hang Zhao, Jiahao Wang | cs.CL | 2026-09-07 |
| #41 | Ambient @ EgoProactive 2026 : Proactive Egocentric Assistance with Visually Grounded Supervision | Logesh Kumar Umapathi | cs.CV | 2026-09-07 |
| #42 | Mind the Gap: Exposing LLM Translation Blind Spots Using the AlphaMWE Multilingual Parallel Corpus | Lifeng Han, Jiahui Liang, Anna Latusek +6 | cs.CL | 2026-09-06 |
| #43 | A Statistical and Machine Learning Framework for Quantifying Offensive Impact in Professional Box Lacrosse | Robert Jimerson | cs.LG | 2026-09-06 |
| #44 | Causal Attribution for Agentic Decisions: Estimators, Coupling, and a Traceability Specification | Ajay Pravin Mahale | cs.AI | 2026-09-06 |
| #45 | The History Is the Detector: Executing CVE Patch History, End-to-End | Qiushi Wu, Kevin Eykholt, Youngja Park +4 | cs.CR | 2026-09-04 |
| #46 | Large Language Models for HVAC Operations in Building Energy Systems: A Critical Review of Methods, Applications, and Deployment Readiness | Alexander Neubauer, Tianzhen Hong, Han Li +4 | cs.AI | 2026-09-04 |
| #47 | Uncensored Open-weight Models: Redistribution as the Persistence Layer | 10a Labs, :, Juliette Garcia +7 | cs.AI | 2026-09-04 |
| #48 | Artificial Intelligence in Equity and Crypto Markets: Progress, Profitability Evidence, and the Limits of Automated Investing | Linsen Zhu, Mengqing Cai | cs.AI | 2026-09-04 |
| #49 | TourPhysics: Bringing Physics to World Models for Exploration and Manipulation from a Single Image | Xin Zhang, Yabo Chen, Zixuan Duan +4 | cs.CV | 2026-09-04 |
| #50 | From Language Models to World-Acting Systems: Progress and Limits of Agentic AI across Digital, Social, Virtual, and Physical Environments | Linsen Zhu, Mengqing Cai | cs.AI | 2026-09-04 |