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4,861 results for “keyword:"lm"” in ICLR 2027. 940 withdrawn or desk rejected listed apart.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]Can Correctness Readouts Choose the Right Answer? A Question-Level Audit of Compact KV-Cache Signals▼1361.33
[PDF]Wide Exploration, Localized Escape: High-Dimensional Branching Dynamics of Multi-Turn Jailbreaks▼4.3k2.00
[PDF]Diagnosing Recoverability: Suppression-Like vs. Overwrite-Like Capability Loss in LLM Post-Training▲3912.67
[PDF]Rewind-OPD: Discrepancy-Guided Trajectory Rollback for On-Policy Distillation in Agentic Tasks▼4.5k2.67
[PDF]MoE-VQ: A Model-Agnostic Gaussian Vector Codebook for 2-Bit Expert Weight Quantization▼4.3k2.00
[PDF]PulmoWorld: An Asynchronous Multimodal Medical World Model for Longitudinal Pneumonia Dynamics▼4.3k2.00
[PDF]BRANCHMEM: Branching Reasoning with Persistent Latent Memory for Language Model Agents▼1.2k1.67
[PDF]Interpolated Policy Distillation: A Controllable Continuum Between Off-Policy and On-Policy Distillation▲9.2k2.67
[PDF]Breaking the Environment Wall: A Unified Framework for Preparing and Evolving Agent-Native Environments▲3912.67
[PDF]Accelerating Global optimisation with Piecewise-Linear Kolmogorov-Arnold Network Surrogates▼5.9k2.33
[PDF]Big-Big-SycoBench: A Benchmark to Detect Sycophancy Through Model Responses to Valid vs. Invalid Arguments▼1.2k1.67
[PDF]OriGent: Post-Training Hardware Engineering Agents through Scalable Environment Synthesis▼5.9k2.33
[PDF]Lead into Gold: The Surprising Effect of Symbolically Generated Deduction Data on LLMs▲3.0k2.33
[PDF]StarOR: Synergizing Tree Search and Test-Time Reinforcement Learning for Optimization Modeling▲14k3.00
[PDF]Weights or KV Cache? Where Activation Sparsity and KV-Cache Sparsity Cross in LLM Decoding▼1361.33
[PDF]Operator-Valued Q-Learning: Compositional Bellman Recursions for Order-Sensitive Decision Making▼5.9k2.33
[PDF]P2TPO: Structure-Aligned Page-to-Token Credit Assignment for Full-Page Document Parsing▲3912.67
[PDF]Online Preference Learning via Generalized Linear Models: Monotonicity and Convergence of SGD▲3.0k2.33
Withdrawn or desk rejected (940)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