CASS: Contribution-Aware Structured Sparsity for Model Merging
cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Terminology
Sources
- Program Synthesis with Large Language Models
- Whoever Started the Interference Should End It: Guiding Data-Free Model Merging via Task Vectors
- Deep Learning for Classical Japanese Literature
- Weight-sparse transformers have interpretable circuits
- MergeBench: A Benchmark for Merging Domain-Specialized LLMs
- Measuring Massive Multitask Language Understanding
- Measuring Mathematical Problem Solving With the MATH Dataset
- Editing Models with Task Arithmetic
- EvoGM: Learning to Merge LLMs via Evolutionary Generative Optimization
- Dataless Knowledge Fusion by Merging Weights of Language Models
- Tulu 3: Pushing Frontiers in Open Language Model Post-Training
- RoBERTa: A Robustly Optimized BERT Pretraining Approach
- No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces
- In-context Learning and Induction Heads
- Emotion Concepts and their Function in a Large Language Model
- FusionBench: A Unified Library and Comprehensive Benchmark for Deep Model Fusion
- Merging Multi-Task Models via Weight-Ensembling Mixture of Experts
- Localizing Task Information for Improved Model Merging and Compression
- Magicoder: Empowering Code Generation with OSS-Instruct
- Retrieval Head Mechanistically Explains Long-Context Factuality
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems