Knowledge Distillation

Long-Chain Reasoning Distillation via Adaptive Prefix Alignment ACL 2026 LoST: Level of Semantics Tokenization for 3D Shapes CVPR 2026 MARD: Module-Aware Reasoning Distillation for Language Models with Adaptive Supervision ACL 2026 Masking Teacher and Reinforcing Student for Distilling Vision-Language Models CVPR 2026 MIND: From Passive Mimicry to Active Reasoning through Capability-Aware Multi-Perspective CoT Distillation ACL 2026 Momentum Memory for Knowledge Distillation in Computational Pathology CVPR 2026 MotionEnhancer: Leveraging Video Diffusion for Motion-Enhanced Vision-Language Models CVPR 2026 MTA: Multi-Granular Trajectory Alignment for Large Language Model Distillation ACL 2026 Multi-Granularity Semantic Revision for Large Language Model Distillation ACL 2026 Online Data Curation for Object Detection via Marginal Contributions to Dataset-level Average Precision CVPR 2026 Prompt-Anchored Vision-Text Distillation for Lifelong Person Re-identification CVPR 2026 Prompt-Level Distillation: A Non-Parametric Alternative to Model Fine-Tuning for Efficient Reasoning ACL 2026 Protecting Language Models Against Unauthorized Distillation through Trace Rewriting ACL 2026 RADAR: Risk-Aware Distilled Adaptive Routing for Efficient Short-Form Video Platform Ecosystem Governance ACL 2026 ReasMark: A Robust Watermark for Attributing LLM Reasoning Under Knowledge Distillation Attacks ACL 2026 Scaling Parallel Sequence Models to Vision Foundation Models CVPR 2026 Semantic Self-Distillation for Language Model Uncertainty UAI 2026 SG-LoRA: Semantic-guided LoRA Parameters Generation CVPR 2026 SharVeT: Similarity-aware Parameter Sharing with Vector-based Tuning for Efficient LLM Compression ACL 2026 SigLino: Efficient Multi-Teacher Distillation for Agglomerative Vision Foundation Models CVPR 2026 SkillSight: Efficient First-Person Skill Assessment with Gaze CVPR 2026 SRA: Span Representation Alignment for Large Language Model Distillation ACL 2026 Streamlined Knowledge Distillation CVPR 2026 Sylloscope at SemEval-2026 Task 11: Decoupling Logic from Belief via DeepSeek-Enhanced Distillation in Qwen Models SemEval 2026 TALAS: Teacher-Anchored Layer Alignment with Adaptive Sharpness-Aware Minimization for Embedding Distillation ACL 2026