Direct-decision models turn text into low-latency structured labels and scores, making them attractive for classification and automatic evaluation. Yet reliability requires more th...
Precise grounding matters. It specifies which object is the target and where that object is, even in clutter and for tiny objects, and it has to be fast enough for closed-loop cont...
Evolutionary search with large language models (LLMs) can stall when progress requires external knowledge the model lacks. Supplying relevant documents helps, but simply adding web...
We present Game-Guided Skill Discovery (GGSD), a framework that uses self-play in games to discover motor skills that are directly playable by humans. Playable skills provide a com...
Visual perception is conventionally formulated as a one-shot prediction from a single glance at the image, under the assumption that the image content and the model's parametric kn...
Video world models are expected to predict how the physical world evolves, yet they often produce visually plausible videos that violate basic physical principles. Existing approac...
High-compression tokenizers are essential for scaling latent image generative models. However, aggressive compression creates a fundamental tradeoff between reconstruction fidelity...
Text-to-image diffusion models are personalized to a subject by DreamBooth fine-tuning on a handful of its images. Increasingly, these images come from a diffusion model rather tha...
Latent communication enables multi-agent systems to exchange information directly in internal representation space, reducing the token, computation, and latency overhead of text-ba...
Latent world models rely on representation geometry for planning, yet regularizing the latent marginal alone does not determine the state-to-state relationships used for action sel...
Reconstructing dynamic driving scenes from recorded sensor data supports closed-loop evaluation of autonomous driving systems by synthesizing observations beyond the original traje...
Autoregressive models are trained to predict a system's behavior one step at a time, and recursive generation allows the learned dynamics to unfold over long horizons. To what exte...
Recent advances have enabled unified omni-modal models in understanding audio, vision, and language. However, existing benchmarks, training data, and learning methods largely treat...
Vision-Language Models (VLMs) have shown strong multimodal reasoning capabilities, yet whether they truly capture the physical consistency underlying real-world dynamics remains un...
Recent video-based world models pair the scalability of autoregressive (AR) prediction with the visual quality of diffusion models. The choice of scene tokenizer is paramount for t...
Long-term egocentric video enables personalized AI assistants to reason about daily life. However, as video histories grow to hundreds of hours spanning months or years, reprocessi...
Large language models rely heavily on human text, which often conveys surface answers rather than the spatial and structural logic behind them. Protein folding is a natural testbed...
Legal language models require reward signals that capture not only answer correctness but also the multidimensional quality of legal responses. Existing reward methods, however, of...
Large Vision-Language Models (LVLMs) have made remarkable progress across visual perception tasks, yet spatial reasoning remains a persistent weakness, especially for questions tha...
Foundation models can serve as clinical agents through tool-use harnesses. However, conventional medical benchmarks assess reasoning over preselected evidence rather than the abili...
Self-supervised learning draws inspiration from infant visual development, yet standard training pipelines bear little resemblance to it: images are independently sampled and globa...
Video generation has rapidly progressed from short, low-quality clips to high-resolution, long-duration sequences with complex spatiotemporal dynamics. Despite strong generative pr...
Self-attention gives LLMs fine-grained, query-dependent access to context, but dense token interactions incur quadratic prefill cost and a key--value cache growing with context len...
AI-generated content, often called AI slop, is increasingly common everywhere, particularly in academia. Slop in AI-generated scientific papers, however, has more complex patterns ...