parameter updates
- Adaptive Gradient Masking for Balancing ID and MLLM-based Representations in Recommendation
- Dr. RAW: Towards General High-Level Vision from RAW with Efficient Task Conditioning
- Hippocampal-like Sequential Editing for Continual Knowledge Updates in Large Language Models
- LLM Unlearning via Neural Activation Redirection
- Merging on the Fly Without Retraining: A Sequential Approach to Scalable Continual Model Merging
- Multi-Modal Interactive Agent Layer for Few-Shot Universal Cross-Domain Retrieval and Beyond
- PALQO: Physics-informed model for Accelerating Large-scale Quantum Optimization
- Some Optimizers are More Equal: Understanding the Role of Optimizers in Group Fairness
- The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning