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
11,175 results for “keyword:"ct"” in ICLR 2027. 3,079 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]VOICE OR LENGTH? COUNTERFACTUAL AUDITING OF TIMING SHORTCUTS IN AUDIO DEEPFAKE DETECTION▼1.2k1.67
[PDF]The Selection Rule Decides the Winner: A Pre-Registered Audit of Open-Set Graph Anomaly Detection▼4.3k2.00
[PDF]LLM Agent Refusal Can be Harmful: An Availability Attack through MITM Tampering on Remote MCP Services▼4.3k2.00
[PDF]Learning to Copy, Learning to Depend: Language Models Offload In-Context Copying to a Pointer Head▼1.3k1.75
[PDF]Built to Read, Not to Recall: Language Skills over World Knowledge in Small Language Models▼1.2k1.67
[PDF]Beyond Endpoint Sufficiency: Inner-Time Trajectory as a Representation Channel in Iterative Systems▼1.3k1.75
[PDF]Reconstruction, Not Localization: A Mechanistic Account of Sparse-Feature OOD Detection in Vision Transformers▼1351.33
[PDF]Extending Controllability from Composition and Topology to Domain Identity in Language-Model Protein Generation▲5073.00
[PDF]Learning to Teach, Learning to Play: Dual Reinforcement Learning with Active Trajectory Inquiry▼4.3k2.00
[PDF]Not Order but Support: Curriculum Effects on Grokking Are a Transient-Support Phenomenon▲14k3.00
[PDF]Navigating the OCEAN: An Atlas of Big Five Personality Representations in Language Models▲8.9k2.75
[PDF]Learning Continuous-time Dynamics Guidance for Diffusion-based Spatiotemporal Reconstruction▼1.2k1.67
[PDF]When LLMs Bid Rationally, and When They Don't: A Traceable Capability Split in Sealed-Bid Auctions▼1351.33
[PDF]OUTPUT WITHOUT WARRANT: SPECTRAL DIMENSION READOUTS CANNOT CERTIFY THEIR OWN HYPOTHESES▲6.1k2.00
[PDF]FlowPlan: Flow-Matching Trajectory Planning Guided by Counterfactual Interaction Consequences▼5.9k2.33
[PDF]Bridges over Heavy Hitters: A Causal-HITS Theory and Counterfactual Benchmark for Attention-Graph KV-Cache Compression▲252.75
[PDF]Verifiable Grounded Generation for Road Damage Reports with Revisable Evidence Contracts▼1351.33
[PDF]Safe Executions Can Hide Policy Failure: A Proposal-Level Audit of Hybrid Control in Synthetic Interviews▲2.0k1.50
[PDF]AVQ-Attention-2: Adaptive Vector-Quantized Attention with Exact Local Blocks and Linear-Cost Training▲9.2k2.67
Withdrawn or desk rejected (3,079)
[PDF]Importance Is Not Gauge-Invariant: Measuring, Not Estimating, Unit Redundancy in LLMsWithdrawn2.00
[PDF]One View, One Action: Spatially Generalizable VLAs through Observation-Aligned Experts and Cross-Graph ConsistencyDesk rejected
[PDF]FlashMask: Importance and Uncertainty-Guided Selective Mask Learning for Semi-Structured LLM PruningDesk rejected
[PDF]SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled AgentsWithdrawn1.33
[PDF]Hand2Robot: Object-Centric 4D Hand Reconstruction from Human Demonstrations for RoboticsWithdrawn2.33