Large Language Models

Revisiting Multimodal KV Cache Compression: A Frequency-Domain-Guided Outlier-KV-Aware Approach CVPR 2026 Revisiting Non-Verbatim Memorization in Large Language Models: The Role of Entity Surface Forms ACL 2026 Revisiting Pipeline Parallelism for LLM Serving OSDI 2026 Revisiting the Reliability of Language Models in Instruction-Following ACL 2026 Revisiting the (Sub)Optimality of Best-of-N for Inference-Time Alignment COLT 2026 Reward Alignment Optimization: A Direct Point-wise Alignment Approach ACL 2026 Reward Modeling for Scientific Writing Evaluation ACL 2026 ReX-MLE: The Autonomous Agent Benchmark for Medical Imaging Challenges MIDL 2026 RFS-Guard: Detecting Reasoning Hallucinations via Cross-Phase Routing Focus in Large Reasoning Models ACL 2026 Rhetorical Questions in LLM Representations: A Linear Probing Study ACL 2026 RIMRULE: Improving Tool-Using Language Agents via MDL-Guided Rule Learning ACL 2026 RiskLab: A Controlled Toolkit for Probing Emergent Risks in LLM-Based Multi-Agent Systems ACL 2026 River-LLM: Large Language Model Seamless Exit Based on KV Share ACL 2026 RLBoost: Harvesting Preemptible Cloud Resources for Cost-Efficient Reinforcement Learning on LLMs NSDI 2026 RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization ACL 2026 RLSeek: Evidence-Grounded Reasoning for RAG Hallucination Detection ACL 2026 RNED: Rotary Number Encoding and Decoding for Medical VLMs CVPR 2026 RoBSA: RoPE-based Blockwise Sparse Multi-head Latent Attention ACL 2026 Robust Membership Inference for Large Language Models under Adversarial Generative Corruption ACL 2026 RobustRL: Role-Based Fault Tolerance System for RL Post-Training OSDI 2026 Robust Tool Use via Fission-GRPO: Learning to Recover from Execution Errors ACL 2026 RollPacker: Taming Long-Tail Rollouts for RL Post-Training with Tail Batching NSDI 2026 ROSE: Rotate Your Large Language Model to See CVPR 2026 Rosetta Stone For Unified MLLMs: A Unified Tokenizer to Decipher Understanding and Generation CVPR 2026 RouteMoA: Dynamic Routing without Pre-Inference Boosts Efficient Mixture-of-Agents ACL 2026