🏢 Shanghai Jiao Tong University

LEGION: Grounding and explaining synthetic image detection and refinement via multimodal learning.

FluxViT: Flexible video models via adaptive token selection for efficient deployment!

ADC: Human-robot collaboration revolutionizes data collection, slashing data needs and boosting robot learning!

Q-Eval-100K: A new, large dataset for evaluating visual quality and text alignment in AI-generated content.

Mask-DPO: Fine-grained Factuality Alignment improves LLMs’ factuality by masking sentence-level errors during DPO training for enhanced knowledge alignment.

SIFT: Grounds LLM reasoning with ‘Stickers’ to highlight context and improve accuracy without extra training.

Show-o Turbo dramatically speeds up multimodal understanding and generation by leveraging parallel decoding and consistency distillation, achieving significant performance gains with fewer sampling st…

iFormer: A new family of mobile hybrid vision networks that expertly blends ConvNeXt’s fast local feature extraction with the efficient global modeling of self-attention, achieving top-tier accuracy a…

PC Agent: While you sleep, AI works! This AI system uses human cognition transfer to perform complex digital tasks, exceeding the capabilities of existing digital agents by efficiently learning from h…

Soccer video understanding gets a major boost with SoccerReplay-1988, the largest multi-modal dataset, and MatchVision, a new visual-language model achieving state-of-the-art performance on event clas…