acceptodds: the papers of ICLR 2027
33,035 results for “keyword:"r"” in ICLR 2027. 8,265 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Efficient Spatio-Temporal Grounding with Multimodal Large Models via Second-Level Tracking and RL Verification▼1431.50
[PDF]DF-Fuzz: Dependency-Guided Context Retrieval for LLM-Assisted Language Processor Fuzzing▼5.9k2.33
[PDF]BEYOND LOCAL RECONSTRUCTION: GEOMETRY- PRESERVING OUTPUT ALIGNMENT FOR BINARY LLM QUANTIZATION▲3.1k2.33
[PDF]When Can Agents Forget Their Reasoning? ICLR for Long-Horizon Agent Context Compression▲3.1k2.33
[PDF]Towards a Transferable Foundation Retriever for Multi-Hop Reasoning over Knowledge Graphs▼4.3k2.00
[PDF]AttentionInfluence: Training-Free Weak-to-Strong Pretraining Data Selection via Attention Head Masking▼4.5k2.67
[PDF]ReState: Enabling Cross-Query KV Reuse for Training-Free Acceleration of BERT Rerankers▲4673.00
[PDF]Annealed Sinkhorn with Momentum: Certified Unregularized Optimal Transport in Linear Memory▲3.1k2.33
[PDF]Fixed Dimension Matters: Tight Complexity and Computational Hardness for Higher-Order Smooth Nonconvex Stationarity▲4673.00
[PDF]Learning What to Preserve: Parameter Attribution for Continual Learning in Large Language Models▲9.3k2.67
[PDF]What the Nonnegative Lens Misses: Energy-Matched Causal Tests of the J-Space in Open Language Models▲31.00
Withdrawn or desk rejected (8,265)
[PDF]Mind Your Marginals: What Governs Fidelity in Linearized Hierarchical Optimal Transport?Desk rejected1.00
[PDF]A Window Is Not a Door: Mapping the Limits and Conditions of Knowledge Editing in Language ModelsDesk rejected2.33
[PDF]Same-Checkpoint Intervention on Pre- and Post-Context States in Entity-Local Temporal EncodersWithdrawn1.33
[PDF]Pulse2View: Same-Sensor Cross-View Pre-Training for Patient-Level Multi-Disease Classification from Wearable PPGWithdrawn1.67