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
424 results for “keyword:"swe"” in ICLR 2027. 120 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Fork Where the Model Changes Its Mind: Belief-Shift Branching for Tree-Structured Reinforcement Learning▼1.2k3.00
[PDF]Towards a Transferable Foundation Retriever for Multi-Hop Reasoning over Knowledge Graphs▼4.3k2.00
[PDF]TAKE THE HINT OR PUSH BACK? DECIDING WHEN A VISION-LANGUAGE MODEL SHOULD ACCEPT THE USER’S ANSWER▼1.2k3.00
[PDF]EvidenceGate: Evidence-Guided Commit-or-Repair Decisions for First-Hop Answers in Multi-Hop Question Answering▼1.2k1.67
[PDF]Look Twice: Training-Free Evidence Highlighting for Knowledge-based Visual Question Answering▼4.5k2.67
[PDF]When Richer Preferences Do Not Help: Rubric Redundancy, Pair Selection, and Training Exposure in Scientific QA▼4.3k2.00
[PDF]CrossTimeBench: Benchmarking Cross-Temporal Video Reasoning in Complex Multi-Event Scenarios▼1.3k1.75
[PDF]GazeWarp: Gaze-Guided Adaptive Warping for Bandwidth-Efficient Multimodal Interaction in XR▼5.8k2.33
[PDF]DiVE: Test-Time Scaling of Direct Visual Exploration via Cross-Trajectory Verification▼1.2k3.00
[PDF]Finding Answers in Thought Matters: Revisiting Evaluation on Large Language Models with Reasoning▼1.2k1.67
[PDF]Everything a Correct Answer Never Told You: Learning from Expert-Corrected Explanations in Colonoscopy Video QA▲9.2k2.67
[PDF]Rethinking Code Localization through Repair-Context Completeness: From Structural and Code Coverage Analysis to Context Augmentation▼1361.33
[PDF]CAER: Conflict-Aware Evidence Refinement for Knowledge-Based Visual Question Answering▼4.3k2.00
[PDF]EviVQA: A Dataset and Benchmark for Evidence-Grounded Evaluation of E-Commerce Visual Question Answering▼4.3k2.00
[PDF]TraceGen: Synthesizing Difficulty-Controllable Bugs for Training and Evaluating Code Repair Agents▼1361.33
[PDF]A Pre-Registered Audit of Hierarchical Retrieval: Cost, Utility, and Assignment Confidence▼1361.33
[PDF]Doctor-RAG: A Failure-Aware Repair Framework for Agentic Retrieval-Augmented Generation▼4.3k2.00
[PDF]Learn from Whoever Is Right: Per-Sample Answer Verification for Multi-Teacher On-Policy Distillation▼1.2k1.67
[PDF]SceneRoute-AVQA: Scene-Conditioned Trustworthy Fusion for Audio-Visual Question Answering Under Multimodal Degradations▼1361.33
[PDF]SYNERGATE-RAG: Learning Graph-Grounded Process Rewards for Multi-Hop Question Answering▼12k1.67
[PDF]IKBQA-R1: Reinforcing Large Language Models for Question Answering over Incomplete Knowledge Graphs▲3.0k2.33
Withdrawn or desk rejected (120)
[PDF]Beyond Online Accuracy: What Persists After Continual Test-Time Adaptation of Multimodal LLMs on Multiple-Choice VQA?Withdrawn1.67
[PDF]Most of the Gain Is Not Video: Taking Apart a Fine-Tuned Video Question-Answering ScoreWithdrawn1.67
[PDF]PathoDC-VQA: Constructing Difficulty-Controlled Pathology VQA Data from Sparse CaptionsDesk rejected2.00
[PDF]Commit Order, Not Commit Rate: Answer Availability and Prefix Preservation in Diffusion Language ModelsWithdrawn1.67