| A Systematic Study of Cross-Layer KV Sharing for Efficient LLM Inference | Oct 18, 2024 | Language ModelingLanguage Modelling | CodeCode Available | 2 |
| On the Role of Attention Heads in Large Language Model Safety | Oct 17, 2024 | AttributeLanguage Modeling | CodeCode Available | 2 |
| WeatherDG: LLM-assisted Diffusion Model for Procedural Weather Generation in Domain-Generalized Semantic Segmentation | Oct 15, 2024 | Autonomous DrivingLanguage Modeling | CodeCode Available | 2 |
| Process Reward Model with Q-Value Rankings | Oct 15, 2024 | Decision MakingLanguage Modeling | CodeCode Available | 2 |
| MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation | Oct 15, 2024 | HallucinationLanguage Modeling | CodeCode Available | 2 |
| Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function Optimization | Oct 11, 2024 | GSM8KLanguage Modeling | CodeCode Available | 2 |
| OneRef: Unified One-tower Expression Grounding and Segmentation with Mask Referring Modeling | Oct 10, 2024 | Language ModelingLanguage Modelling | CodeCode Available | 2 |
| TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text | Oct 10, 2024 | Language ModelingLanguage Modelling | CodeCode Available | 2 |
| Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs | Oct 10, 2024 | Active LearningLanguage Modeling | CodeCode Available | 2 |
| Q-VLM: Post-training Quantization for Large Vision-Language Models | Oct 10, 2024 | Language ModelingLanguage Modelling | CodeCode Available | 2 |