Key papers

• Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning (2026)
  Junyao Yang et al.
  11.77
• AutoIndex: Learning Representation Programs for Retrieval (2026)
  Sam O'Nuallain et al.
  10.70
• CausalMix: Data Mixture as Causal Inference for Language Model Training (2026)
  Zinan Tang et al.
  10.60
• H$^2$SD: Hybrid Hindsight Self-Distillation (2026)
  Qiye Cai et al.
  8.24
• Understanding Reasoning from Pretraining to Post-Training (2026)
  Jingyan Shen et al.
  7.98
• Verbalizable Representations Form a Global Workspace in Language Models (2026)
  Wes Gurnee et al.
  7.07
• Operational Hallucination and Safety Drift in AI Agents (2026)
  Shasha Yu et al.
  5.49
• Supra Cognitive Modes: A Routed Architecture for Agent Memory (2026)
  Joshua Tobkin et al.
  5.49
• Agents in the Wild: Where Research Meets Deployment (2026)
  Grace Hui Yang et al.
  5.49
• On the Role of Directionality in Structural Generalization (2026)
  Zichao Wei
  5.01
• T^2MLR: Transformer with Temporal Middle-Layer Recurrence (2026)
  Ziyang Cai et al.
  5.01
• Design-Based Supervised Learning with Noisy Human Labels (2026)
  Robert Chew et al.
  5.01
• More with Less: a Large Scale Remote Sensing VLM with a Simple Recipe (2026)
  Stefan Maria Ailuro (INSAIT et al.
  5.01
• Attention-Guided Saliency Maps for Interpreting Visualization Literacy in VLMs (2026)
  Maeve Hutchinson et al.
  5.01
• Relay-Bench: Evaluating LLMs on Multi-Domain Reasoning Chains (2026)
  Liam Swayne
  5.01
• Structured Output Collapses Answer Diversity Across 44 Language Models (2026)
  Tapan Parikh
  5.01
• Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA (2026)
  Shaswata Mitra et al.
  5.01
• AILQA: Evaluating AI-Driven Legal Question Answering Systems for the Indian Legal System (2026)
  Shubham Kumar Nigam et al.
  5.01
• Verifiable Self-Evolution for Open-Ended Dialogue Skills via Future-Feedback Prediction (2026)
  ChaoJin Zhao et al.
  5.01
• AutoJourn: Multi-Perspective Summarisation, Bias Detection and Bias Neutralisation for LLM-Generated News in Automated Journalism (2026)
  Himel Ghosh et al.
  5.01
• MIRA-Ev:A Benchmark for Granular Evidence Detection and Relational Reasoning in Clinical Exams (2026)
  Iker De la Iglesia et al.
  5.01
• The Price of Reasoning: Cost-Quality Tradeoffs in Reinforcement Learning for Neural Machine Translation (2026)
  Michael Jungo et al.
  5.01
• Prompt Design at Scale: How Format, Instruction Count, and Context Length Shape Instruction Adherence and Hallucination in Large Language Models (2026)
  Netanel Eliav
  5.01
• Multi-Head Recurrent Memory Agents (2026)
  Jiatong Li et al.
  4.39
• Training, Reading, and Editing Legible Transformers (2026)
  Mark Oskin
  4.39
• Git-Assistant: Planning-Based Support for Updating Git Repositories (2026)
  Alfredo Garrach\'on Ruiz et al.
  4.39
• Are we Merging the Right Models? Impact of Expert Training Duration on Model Merging for LLMs (2026)
  Nikita Kozodoi et al.
  4.39
• Ask Before You Diagnose: Safe-Psych, a Sequential Evaluation Benchmark for LLMs in Psychiatry (2026)
  Oriana Presacan et al.
  4.39
• The Hitchhiker's Guide to Monoculture (2026)
  Gordon Burtch
  4.39
• Improving Molecular Property Prediction in Small Language Models Using Graph-based Tools (2026)
  Konstantinos Bougiatiotis et al.
  4.39
• RAGthoven at SemEval-2026 Task 1: A Multi-Stage Pipeline Walks Into a Benchmark and Barely Clears the Bar (2026)
  Marek \v{S}uppa et al.
  4.39
• GFlowRL: Scaling Distribution-Matching RL to Large Language Models (2026)
  Xiaodong Liu et al.
  4.39
• Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignment (2026)
  Dwip Dalal et al.
  4.39
• Attention-Free and Lightweight Token Reduction for Efficient Vision-Language Models (2026)
  Xuanyi Hao et al.
  4.39
• Barnamala: Parameter-Efficient Handwritten Devanagari Recognition at Benchmark Saturation (2026)
  Ashish Thapa et al.
  4.39
• Groc-PO: Grounded Context Preference Optimization for Truthful Multimodal LLMs (2026)
  Zhixiao Zheng et al.
  4.39
• Algebraic Representability as the Limiting Regime of Grokking: An Exactly Solvable Model with Holomorphic Activations (2026)
  Chon-Fai Kam et al.
  4.39
• Rethinking Speech Foundation Model Fine-tuning: Better SFT or Better Match? (2026)
  Wangjin Zhou et al.
  4.39
• Beyond a Joke: Multi-Angle Reasoning for Detecting and Explaining Harmful Humor in Memes (2026)
  Shanhong Liu et al.
  4.39
• Relevant and Irrelevant: A Renormalization Group Analysis of Transformer Attention (2026)
  Parviz Haggi-Mani et al.
  4.39
• Kolmogorov--Arnold Networks for Small Language Models (2026)
  Felippe Alves et al.
  4.39
• Toward Federated Multimodal Graph Foundation Models: A Topology-Aware Multimodal Alignment Framework (2026)
  Xunkai Li et al.
  4.39
• AuEmoChat: Authentic Emotion Understanding and Rendering for Conversational Speech Synthesis (2026)
  Zhenqi Jia et al.
  4.39
• In-context learning of closed form solution to simple linear regression task using transformer with linear self-attention (2026)
  Katsuyuki Hagiwara
  4.39
• Candidate Attended Dialogue State Tracking Using BERT (2026)
  Junyuan Zheng et al.
  4.39
• Reliability Scales Inversely: Bigger Models Compound Mistakes Faster via a Hidden Auto-Regressive Risk Regime (2026)
  Kushal Chakrabarti
  4.39
• Binding Drift in Multi-Step Tool-Augmented Agents (2026)
  Rahul Suresh Babu et al.
  4.39
• A Controlled Study of Attention-Only Transformers (2026)
  Henry Ndubuaku et al.
  4.39
• CANDOR: Chance-Calibrated Discordance in Frozen Foundation Encoders (2026)
  Soroosh Tayebi Arasteh et al.
  4.39
• Decodable but Not Detectable: A Leakage Fingerprint for Near-OOD Benchmarks (2026)
  Vishnu Bindu Balachandran
  4.39
• Multi-Mask Diffusion Language Models for Few-Step Generation (2026)
  Sijin Chen et al.
  4.39
• The Blessing of Dimensionality: How Near-Orthogonality in High-Dimensional Spaces Explains Temporal Portability (2026)
  Abigail Woodring et al.
  4.39
• TokenScope: Token-Level Explainability and Interpretability for Code-Oriented Tasks in Large Language Models (2026)
  Amirreza Esmaeili et al.
  3.51
• Scaling Point-in-Time Language Models (2026)
  Bryan Kelly et al.
  3.51
• Real-World Evaluation of an AI Agent Drafting Translational Impact Summaries (2026)
  Mohammad Arvan et al.
  3.51
• Recovering Input Text from Hidden States: Study of Gradient-Based Inversion of Decoder-Only Language Models (2026)
  Miko{\l}aj S{\l}owikowski et al.
  2.00
• Behavior-Adaptive Conversational Agents: Toward a Fluid Personality Framework (2026)
  Hasibur Rahman et al.
  2.00
• Adversarial Pragmatics for AI Safety Evaluation: A Benchmark for Instruction Conflict, Embedded Commands, and Policy Ambiguity (2026)
  Brett Reynolds
  2.00
• Infinity-Parser2 Technical Report (2026)
  Zuming Huang et al.
  2.00
• Discriminative Regularization for Generative Models (2016)
  Alex Lamb et al.
  —