Decodable but Misrouted: Sparse Features Uncover a Readout Gap in Vision-Language Models for Harmful Meme Detection
Research
Research News
New papers, breakthroughs and academic AI research
When the Right Answer Is Missing: An Arithmetic-Dependent Rejection Bottleneck in Jev
Research
CIDER-FM: Foundation Models for Causal Inference from Diverse Experimental Regimes
Research
Less Data, Better Timing: Student-Curriculum Coupling for VLM On-Policy Distillation in Temporal Video Grounding
Research
Parameterization method of reservoir properties for ensemble-based data assimilation using intermediate latent space of StyleGAN
Research
Towards Robust Time Series Learning via Capacity-Centric Modulation
Research
Reconstructing the Dynamic World: A Representation-Centric View of 4D Scene Reconstruction
Research
CoEvoWhen: Policy-Tool Coevolution for Ultra-Long Video Temporal Grounding
Research
Can Domain Generalization be Guaranteed in Small-Sample Learning?
Research
Enhancing Autoregressive Video Generation via Representation Adversarial Distillation
Research
LongEmo: Towards Emotion Understanding and Reasoning in Long Videos
Research
ECHO-G: Embodied Co-speech Humanoid mOtion Generation
Research