NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
8,677 results for “keyword:"language"” in ICLR 2027. 2,084 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Hyperbolic Detoxification for Vision-Language Model Safety via Intent-Risk Calibration▼5.9k2.33
[PDF]TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on a Consumer-Grade GPU with <1 GB VRAM▲2833.00
[PDF]Beyond Continuity Or Discontinuity: Zigzag Algebra for Compositional Relations in Low-Rank Adaptation▼1.2k1.67
[PDF]GraphPilot: Faithful and Adaptive Reasoning for Large Language Models via Graph-Constrained Exploration▲3.0k2.33
[PDF]How Much Does a Reasoning Summary Reveal? An Observability Ladder for Large Language Models▲11.00
[PDF]Broadcast, Reinforce, Repeat: Attention Dynamics Behind Repetition Collapse in Diffusion Language Model Forecasting▲1.7k3.33
[PDF]Models Are Mortal, Measurements Are Not: A Portable, Model-Agnostic Representation for Video Misinformation▲3.0k2.50
[PDF]FOODBOUNDARYBENCH: DO CONVERSATIONAL LLMS HOLD HEALTH BOUNDARIES ACROSS MULTI- TURN RECOMMENDATIONS?▼1611.50
[PDF]WAVE-VLA: A Whole-Body Humanoid VLA with Executable Vision–Motion Codes Learned from Heterogeneous Human and Robot Data▼1.2k1.67
[PDF]ReDiPPO: Reference-Guided Value Calibration and Discrepancy-Aware Token Reweighting for Mathematical Reasoning▲3.0k2.33
[PDF]Mixture-of-LoRA: Modality-Specialized Low-Rank Adapters for Multimodal Language Models▼1.2k1.67
[PDF]What Does Another Loop Buy? Attention Reallocation Tracks the Marginal Value of Test-Time Compute in Looped Transformers▲3822.67
[PDF]CARE: A Consulting, Acquiring, Resource-aware, Explaining Agent for Clinical Decision Support▲3.9k1.67
[PDF]Beyond Fitting: Knowledge-Guided LLM Reasoning for Combinatorial Gene Perturbation Prediction▲3.0k2.33
[PDF]SeeNav-Agent: Enhancing Vision-Language Navigation with Visual Prompt and Step-Level Policy Optimization▼4.3k2.00
[PDF]Sparse AutoEncoders Reveal That MoE Experts Exhibit Human-Interpretable Fine-Grained Specialization▼1.2k1.67
[PDF]PrimitiveVLA: Learning Reusable Motion Primitives for Efficient and Generalizable Robotic Manipulation▼4.5k2.67
[PDF]SAR4CAD: Structure-Aware Reinforcement Learning for Parametric CAD Reconstruction from Multi-View Drawings▲3.0k2.33
[PDF]When to Compile a Computer-Use Agent? Measuring Payback and Making Compilation Decisions for Token Efficiency▼1361.33
[PDF]OphMem: Leveraging Cross-Case Experience to Mitigate Visual Ambiguity in Ophthalmic Surgical Video Understanding▼4.3k2.00
Withdrawn or desk rejected (2,084)
[PDF]A Window Is Not a Door: Mapping the Limits and Conditions of Knowledge Editing in Language ModelsDesk rejected2.33
[PDF]When Is a Policy Violation a Model Failure? Policy Observability and Failure Attribution in Agent-Safety EvaluationDesk rejected
[PDF]NeuroFORM: Neuro-Symbolic Formalization of Legal Rules with Counterexample-Guided RefinementWithdrawn2.00
[PDF]Population Contracts for Scalable Language-Guided Multi-Robot Planning and ControlDesk rejected