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424 results for “keyword:"swe"” in ICLR 2027. 120 withdrawn or desk rejected listed apart.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]CAN RETRIEVAL FAILURES DRIVE GRAPH EVOLUTION? SELF-IMPROVING GRAPHS FOR EVIDENCE RECOVERY IN MULTI-HOP QA▼1.2k1.67
[PDF]DocTrek: Tree-Guided Agentic Reinforcement Learning via Dense Rewards for Document Understanding▼4.3k2.00
[PDF]ECLIPSE: An Executable Contextual Intervention and Planning Agent for Time-Series Tasks▼4.3k2.00
[PDF]SuperMemory-VQA: An Egocentric Visual Question Answering Dataset and Benchmark for Long-Horizon Memory▼4.3k2.00
[PDF]TraceEarth: From Semantic Matching to Spatial Tracing for Training-Free UHR Remote Sensing VQA▲3952.67
[PDF]ComplexLogicalQA: Benchmarking Knowledge Graph Question Answering Beyond Chain-like Reasoning▼4.3k2.00
[PDF]ScaffoldBench: A Dynamic Benchmark for Evaluating Pedagogical Scaffolding and ZPD Alignment in Large Language Models▼4.3k2.00
[PDF]Theta sweeps accelerate cognitive map learning by broadcasting information to unvisited regions▲1.5k3.50
[PDF]Holding the Answer Fixed: What Hidden-State Probes and Interventions Establish About Correctness▼4.3k2.00
[PDF]Beyond Feature Shift: Measuring and Mitigating Output Distribution Collapse in Cross-Domain VQA▼1611.50
[PDF]SVGFaith: A Two-Layer Meta-Evaluation of Faithfulness Metrics for Text-to-SVG Generation▼5.8k2.33
[PDF]QRouter: Question-Conditioned Visual Evidence Routing for Fine-Grained Visual Question Answering▼5.8k2.33
[PDF]DocPilot: Interactive Agent Orchestration and Training for Long Visual Document Understanding▼1.2k1.67
[PDF]RISE: Recurrent Evidence Consolidation with Kernelized Selection for Efficient Long-Video Understanding▼4.5k2.25
[PDF]Semantic Role Projection: Structured Visual Embeddings for Compositional Reasoning in Multimodal LLMs▼1.2k1.67
[PDF]When Formatting Determines Rankings: Separating Semantic Accuracy, Compliance, and Strict Accuracy▼4.5k2.67
[PDF]RS-OPSD: Reliable Privileged On-Policy Self-Distillation For Ultra-High-Resolution Remote Sensing VQA▼1.2k3.00
[PDF]Select, Compress, Reinvest: A Controlled Study of Visual-Token Allocation in Long-Video MLLMs▼1361.33
[PDF]When is seeing enough? Cross-granularity evidence search with Sufficiency verification for High-resolution understanding▼4.5k2.67
[PDF]Grounding Is Not Enough: Testing Evidence Sufficiency in LLM Reasoning over Knowledge Graphs▼1361.33
[PDF]Beyond Chunks and Binary Graphs: Multimodal Hypergraph Representation for Long Document Question Answering▼5.8k2.33
[PDF]KMMG-Agent: A Knowledge–Memory Multi-Graph Agent for Multi-hop Egocentric Question Answering▼4.3k2.00
[PDF]TRACE-SWE: Trajectory Refinement with Action-oriented Execution Evidence for Code Agents▼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