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
4,861 results for “keyword:"lm"” in ICLR 2027. 940 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]EvokeAgent: A Hardware-Aware, Knowledge-Base-Co-Driven Self-Evolving Agent System for GPU Kernel Optimization▼1361.33
[PDF]Keys Decide Attention, Values Decide Contribution: Value-Gated KV Cache Eviction at 20× Compression▼1361.33
[PDF]BitLadder: Bit-Level Selective Loading of the KV Cache for Efficient Long-Context LLM Inference▼4.3k2.00
[PDF]PersonalWorkEnv: Evaluating and Training Personalized AI Assistants with Synthetic Work Environments▲3912.67
[PDF]Inferring Hidden Agentic Logic from Traces for Online Fault Attribution and Workflow Optimization▼4.3k2.00
[PDF]Rubric-Calibrated Preferences: Cross-Query Calibration of LLM Judgments via Item Response Theory▼4.5k2.67
[PDF]MEMSHIELD: NEUTRALIZING COALITIONAL MEMORY POISONING IN LLM AGENTS VIA CAUSAL REPRESENTATION REPAIR▼4.3k2.00
[PDF]Small Executors Derail on Intermediates They Produced Themselves: Compiling Skills into Tools They Can Act On▲20k2.67
[PDF]Do You Even Need More Data? Rethinking LLM Deployment for Label-Scarce Tabular Classification with TabLens▼1611.50
[PDF]Sketch–Solver: Decoupling Construction and Parameterization for Natural-Language CAD Program Synthesis▼1.2k1.67
[PDF]AttendingScorer: An End-to-End Driving Evaluator that Read Out Trajectory Evaluation Score from latent of Vision-Language-Model▼1611.50
[PDF]From Evidence to Effect: Authority Semantics and Runtime Infrastructure for Stateful Agents▼1.2k1.67
[PDF]Kernel-Level Context Parallelism: Bridging Incompatible Shard Layouts in Hybrid Linear-Attention Transformers▲6.1k2.00
[PDF]What Does LLM-Judged Novelty Reward? Controlled Experiments on Context, Workflow, and Measurement Validity▼1361.33
Withdrawn or desk rejected (940)
[PDF]When Is a Policy Violation a Model Failure? Policy Observability and Failure Attribution in Agent-Safety EvaluationDesk rejected
[PDF]-Bench: Benchmarking Proactive Speech Interaction with Full-Duplex Conversational AIDesk rejected