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
642 results for “keyword:"rsa"” in ICLR 2027. 170 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]From Anomalies to Failures: Constructing Causal Error Graphs for Agentic Trace Diagnosis▼12k1.67
[PDF]Stabilizing Slide Representations for Continual Whole-Slide Image Learning: Frozen Attention and Prototype Rehearsal▼4.5k2.25
[PDF]Tight Mistake–Abstention Tradeoffs for Sequential Prediction under Adversarial Injections▼2443.33
[PDF]Discovering Safety Spectra in Autonomous Driving via Constrained Adversarial Self-Play▼4.5k2.67
[PDF]When the Environment Lies: Evaluating Autonomous Penetration Testing Agents under Adversarial Environments▼1361.33
[PDF]Best Friends, Not Forever: Evaluating Long-Horizon Persona Collapse and Behavioral Drift in AI Companions▼1361.33
[PDF]Have I Scene This Before? Spatially Grounded Conversational Memory for Complex Queries in Egocentric Assistants▼5.8k2.33
[PDF]ROBUST-VERIFY: Adversarial Self-Play with Structured Reasoning for Robust Claim Verification under Corrupted Chain-of-Thought▼1.2k1.67
[PDF]ProbeFool: Evading LLM Jailbreak Activation Monitors with Probe-Agnostic Attention Routing▼4.3k2.00
[PDF]Beyond Instruction Override: Benchmarking Indirect Prompt Injection with Task-Tampering Attacks▼5.9k2.60
[PDF]Interpretable Adversarial Defense via Class-Aware Neuron Sensitivity Attribution and Recalibration▼1.2k1.67
[PDF]What makes a good anchor? Offline Anchor Selection for Test-Time Adversarial Robustness of CLIP▼5.8k2.33
[PDF]The Clocks of Composition: Built by the Signal, Lost to Weight Decay, Kept by Rehearsal▼1.2k1.67
[PDF]XSPA: Crafting Imperceptible X-Shaped Sparse Adversarial Perturbations for Transferable Attacks on VLMs▼4.3k2.00
[PDF]PHASE: Packet-level Hierarchical Adversarial Semantic Exploitation for Targeted Steering of Retrieval-Augmented Diffusion Models▼1.2k1.67
[PDF]CLOAKFEM: Agentic FEM Code Generation for Red-Teaming Computational Resource Exhaustion▲13k2.33
[PDF]GenShield: Generalizable Visual Prompts for VLM Jailbreak Defense via Dual-View Adversarial Training▲3.0k2.33
Withdrawn or desk rejected (170)
[PDF]Physical and Evolutionary Constraints on Machine Learning Priors: Reconciling No Free Lunch with Real-World GeneralizationWithdrawn
[PDF]DQ-PAD: Discriminative Quantized Prototype Alignment for Adversarial Patch DefenseWithdrawn1.67
[PDF]AcoustiGym: Physics-Based Acoustic Environment Generation for Robotic Policy EvaluationDesk rejected
[PDF]Forgetting is Competition: Rethinking Unlearning as Representation Interference in Diffusion ModelsWithdrawn1.67