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424 results for “keyword:"swe"” in ICLR 2027. 120 withdrawn or desk rejected listed apart.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]Learning When to Reconsider: Adequacy-Guided Inference-Time Interventions for Histopathology VLM Agents▲14k3.00
[PDF]GazeLens for Efficient Egocentric Video Question Answering with Simple Gaze-Driven Adaptive Token Reduction▼5.8k2.33
[PDF]Zero-LLM Trajectory Search over Line-Lifted Knowledge Graphs: Internalizing Query Decomposition for Multi-Hop RAG▲9.2k2.67
[PDF]Seeing What Should Be Heard: Diagnosing and Repairing Cross-Modal Shortcuts in Omni-Modal LLMs▲3952.67
[PDF]HiR-MKR: Hierarchical Reconstruction and Multi-Source Knowledge Retrieval for Semi-Structured Table Question Answering▼1361.33
[PDF]STQA: A Dataset and Road-Subgraph-Augmented Language Model for Spatiotemporal Traffic Question Answering▲5.7k2.00
[PDF]When Does an Image Determine the Answer? Benchmarking Visual Answerability across Charts and Scenes▼1.2k3.00
[PDF]EOR: Evidence-Obligation Reasoning for Verification-Driven Long-Video Question Answering▼4.3k2.00
[PDF]HiToc: Hierarchical Token Compression Across the Vision-Language Pipeline for Long Document Question Answering▲14k3.00
[PDF]VisExpress: Beyond Rendering—Benchmarking How LLM-Generated HTML Answers Convey Information▼4.3k2.00
[PDF]Reflect Less, Reason Better: Entropy-Aware Reflection Rewards for Efficient Large Reasoning Models▲14k3.00
[PDF]You Only Pass Once: Answering and Abstaining Together in a Single Forward Pass of a Frozen Language Model▲5.4k3.00
[PDF]ORQA: An Occupation-Realistic Question and Answer Framework for LLM Professional Knowledge▼1.3k1.75
[PDF]Simple Links, Strong Retrieval: Local Entity Expansion for Multi-Hop Evidence Retrieval▼1.2k1.67
[PDF]The Change You Want To Talk About: Enabling spatial and narrative Change Detection in Earth Observation with a single VLM architecture▼4.3k2.00
[PDF]CLIMB: A Clinical Multimorbidity Benchmark for Diagnosing Co-occurring Conditions through Multiturn Conversations▼1361.33
[PDF]Verification Mirage: Mapping and Repairing the Reliability Boundary of Self-Verification in Medical VQA▲5103.00
[PDF]Relevance Says Yes, but Sufficiency Says No: Efficient Adaptive Retrieval via Latent Evidence Sufficiency▼4.5k2.67
[PDF]Don't Wear Too Many Hats: Capability Modularization for Multi-Document Analytical Question Answering▲5103.00
[PDF]Diagno-SV: Decoupling Perception, Reasoning, and Knowledge for Trustworthy Medical VLMs▲3952.67
[PDF]Re-Attending to the Missing Pieces: Test-Time Visual Evidence Refinement for High-Resolution Reasoning▲3952.67
[PDF]MARS: Multi-Evidence Adaptive Search with State-Preserving Control for Repository-Level Program Repair▼4.3k2.00
[PDF]DeNovoSWE: Scaling Long-Horizon Environments for Generating Entire Repositories from Scratch▼4.3k2.00
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