ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning
Paper • 2608.03972 • Published • 5
TRESP Lab
university
AI & ML interests
Multimodal AI
Recent Activity
View all activity
Jinhe
submitted a
paper to Daily Papers 25 days ago
Jinhe
authored 14
papers 25 days ago
Dr. DocBench: A Comprehensive Benchmark for Expert-Level and Difficult Document Parsing
Paper • 2606.01393 • Published
MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolution
Paper • 2607.05297 • Published • 1
Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence
Paper • 2606.15932 • Published • 38
Graph is a Substrate Across Data Modalities
Paper • 2601.22384 • Published
AUVIC: Adversarial Unlearning of Visual Concepts for Multi-modal Large Language Models
Paper • 2511.11299 • Published
Does Machine Unlearning Truly Remove Knowledge?
Paper • 2505.23270 • Published
ASCD: Attention-Steerable Contrastive Decoding for Reducing Hallucination in MLLM
Paper • 2506.14766 • Published
Can Visual Input Be Compressed? A Visual Token Compression Benchmark for Large Multimodal Models
Paper • 2511.02650 • Published • 10
MINED: Probing and Updating with Multimodal Time-Sensitive Knowledge for Large Multimodal Models
Paper • 2510.19457 • Published • 9
KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Augmentations and Constraints
Paper • 2510.19316 • Published • 12
Reinforcement Mid-Training
Paper • 2509.24375 • Published • 10
Loong: Synthesize Long Chain-of-Thoughts at Scale through Verifiers
Paper • 2509.03059 • Published • 25
Backdoor Cleaning without External Guidance in MLLM Fine-tuning
Paper • 2505.16916 • Published • 17
PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selection
Paper • 2502.12119 • Published
ShuoChen99
updated 2
collections 11 months ago
gengyuanmax
updated a
Space 11 months ago