ablation study
- Bayesian Optimization with Preference Exploration using a Monotonic Neural Network Ensemble
- Co-PatcheR: Collaborative Software Patching with Component-specific Small Reasoning Models
- Compress & Cache: Vision token compression for efficient generation and retrieval
- MDNS: Masked Diffusion Neural Sampler via Stochastic Optimal Control
- Object-Centric Concept-Bottlenecks
- Transforming Generic Coder LLMs to Effective Binary Code Embedding Models for Similarity Detection
- Unveiling Chain of Step Reasoning for Vision-Language Models with Fine-grained Rewards