FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs
Paper • 2601.13836 • Published • 37
AI & ML interests
None defined yet.
Jinlan
authored a
paper 3 months ago
Jinlan
submitted a
paper to Daily Papers 3 months ago
Jinlan
authored 14
papers 3 months ago
LLM can Achieve Self-Regulation via Hyperparameter Aware Generation
Paper • 2402.11251 • Published • 1
Hint-before-Solving Prompting: Guiding LLMs to Effectively Utilize Encoded Knowledge
Paper • 2402.14310 • Published
CorefDiffs: Co-referential and Differential Knowledge Flow in Document Grounded Conversations
Paper • 2210.02223 • Published
SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model
Paper • 2406.12030 • Published
Cross-Modality Safety Alignment
Paper • 2406.15279 • Published • 5
FlipAttack: Jailbreak LLMs via Flipping
Paper • 2410.02832 • Published • 1
Multi-Layer Visual Feature Fusion in Multimodal LLMs: Methods, Analysis, and Best Practices
Paper • 2503.06063 • Published
VistaDPO: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models
Paper • 2504.13122 • Published • 20
LLM as Effective Streaming Processor: Bridging Streaming-Batch Mismatches with Group Position Encoding
Paper • 2505.16983 • Published • 1
LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models
Paper • 2510.13626 • Published • 47
RoboOmni: Proactive Robot Manipulation in Omni-modal Context
Paper • 2510.23763 • Published • 62
MCM-DPO: Multifaceted Cross-Modal Direct Preference Optimization for Alt-text Generation
Paper • 2510.00647 • Published
AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agents
Paper • 2512.23343 • Published • 30
XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation
Paper • 2104.07412 • Published
Jinlan
authored a
paper about 1 year ago
Jinlan
updated a
model about 2 years ago
Jinlan
authored 2
papers about 2 years ago
From GPT-4 to Gemini and Beyond: Assessing the Landscape of MLLMs on Generalizability, Trustworthiness and Causality through Four Modalities
Paper • 2401.15071 • Published • 37
How Far Are We from Believable AI Agents? A Framework for Evaluating the Believability of Human Behavior Simulation
Paper • 2312.17115 • Published • 2