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
1,547 results for “keyword:"ir"” in ICLR 2027. 379 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]LEMMA: Learned Model Merging for Text-to-Image Generation via Multi-Objective Optimization▼5.8k2.33
[PDF]The Irreversibility Threshold: When Error in LLM Agent Pipelines Outruns Human Correction▼1361.33
[PDF]AutoDojo: A Generative Benchmark for Evaluating Prompt Injection Defenses in LLM Agents▼4.3k2.00
[PDF]A SINGLE-LOOP, CONSTANT-BATCH FIRST-ORDER PENALTY METHOD FOR STOCHASTIC BILEVEL OPTIMIZATION▼2443.33
[PDF]Open-Loop, Closed-Form: Solver-Driven Reservoir Computing for Coarse-Grid PDE Forecasting▼1.2k1.67
[PDF]Byte-Pair Patching: Controllable Dynamic Tokenization for Time-Series Foundation Models▲13k2.33
[PDF]Competitor Interactions and Recall Lifetimes in Spherical Log-Sum-Exp Associative Memory▼1.2k1.67
[PDF]Attribution-guided Pruning for Circuit Discovery and Targeted Correction in Language Models▼4.3k2.00
[PDF]The Arithmetic Error Bar: A First-Passage Law for the Numerical Fragility of Language Models▼1361.33
[PDF]QuARC: A Benchmark for LLM-Generated Quantum Circuits and an Audit of Its Acceptance Region▼1361.33
[PDF]Cultural Counterfactuals: Evaluating Cultural Biases in Large Vision-Language Models with Counterfactual Examples▼5.8k2.33
[PDF]Divide and Inject: Can Agents Reconstruct an Indirect Prompt Injection from Fragments?▲3.0k2.33
[PDF]Spoken-Digit Recognition Without Training: Geometry, Coupling, and Drive Effects in Oscillator Networks▼1.2k1.67
[PDF]Interventional Commutativity: Effect Preservation and Reference Selection Under Weight-Only Quantisation▼1.2k1.67
[PDF]Learning Heterogeneous Tabular Tasks through Multiregime Pretraining of Prior-Data Fitted Networks▼1361.33
[PDF]Counting Capabilities, Not States: Capability Representations for Exploration in Open-Ended Worlds▼1.2k1.67
[PDF]Self-Reflection Fine-Tuning: Enhancing Agent Security against Prompt Injection Attacks from Failure Experience▲3952.67
[PDF]You Got the Right Answer for the Wrong Reason: Process Fairness in Agentic AI via Structured Deliberation▼12k1.67
Withdrawn or desk rejected (379)
[PDF]FairWatch: Interaction Topology as a First-Order Variable Shaping Safety and Fairness in Multi-Agent DeliberationDesk rejected2.00
[PDF]Attested but Unaccounted: DP-SGD Privacy Accounting as a Precondition of Every StepWithdrawn1.67