Large Language Models

Nano-EmoX: Unifying Multimodal Emotional Intelligence from Perception to Empathy CVPR 2026 NCL-UoR at SemEval-2026 Task 5: Embedding-Based Methods, Fine-Tuning, and LLMs for Word Sense Plausibility Rating SemEval 2026 Neuron-Aware Active Few-Shot Learning for LLMs ACL 2026 No Buffer, No Bottleneck: Efficient Zero-Copy KV Cache Offloading for Long-Context LLMs OSDI 2026 Octopus: Gated Selective Attention for Memory-Bounded Long-Context Inference in Large Language Models ACL 2026 OneCAT: Decoder-Only Auto-Regressive Model for Unified Understanding and Generation CVPR 2026 One Task Vector is not Enough: A Large-Scale Study for In-Context Learning ACL 2026 On the Effect of Sampling Diversity in Scaling LLM Inference UAI 2026 PAI at SemEval-2026 Task 3: An LLM and Data Redistribution Adaptation-Based Predictive Strategy for Valence-Arousal Scores SemEval 2026 Parameter-Efficient Adaptation for MLLMs via Implicit Modality Decomposition CVPR 2026 PE-QAT: Parameter-Efficient Quantization-Aware Training for Large Language Models ACL 2026 PointThinker: Point-Incentivized Parallel Thinking for Multimodal Large Language Model CVPR 2026 Practical Guidelines for Model Merging in LLMs Pre-Training ACL 2026 Price of metric universality in vector quantization is at most 0.11 bit COLT 2026 Prism: Cost-Efficient Multi-LLM Serving via GPU Memory Ballooning OSDI 2026 Process Reward Models Meet Planning: Generating Precise and Scalable Datasets for Step-Level Rewards ACL 2026 Quantifying and Understanding Uncertainty in Large Reasoning Models ACL 2026 R-4B: Incentivizing General-Purpose Auto-Thinking in MLLMs via Bi-Mode Annealing and Reinforce Learning CVPR 2026 ReasMark: A Robust Watermark for Attributing LLM Reasoning Under Knowledge Distillation Attacks ACL 2026 ReFTA: Breaking the Weight Reconstruction Bottleneck in Tensorized Parameter-Efficient Fine-Tuning CVPR 2026 Residual Decoding: Mitigating Hallucinations in Large Vision-Language Models via History-Aware Residual Guidance CVPR 2026 Rethinking Data Mixing from the Perspective of Large Language Models ACL 2026 Rethinking MLLM Itself as a Segmenter with a Single Segmentation Token CVPR 2026 Revisiting Pipeline Parallelism for LLM Serving OSDI 2026 SAME: Safety-Aware Model Editing Guided by Safety Transformation ACL 2026