Recent work has shown that diffusion models can generate high-quality images by operating directly on SSL patch features rather than pixel-space latents. Howeve...
Recent progress has rapidly advanced our understanding of the mechanisms underlying in-context learning in modern attention-based neural networks. However, exis...
Large language models have transformed many applications but remain expensive to train. Sparse Mixture of Experts (MoE) addresses this through conditional compu...
Continual reinforcement learning (CRL) requires agents to learn from a sequence of tasks without forgetting previously acquired policies. In this work, we intro...
Training modern large language models (LLMs) has become a veritable smorgasbord of algorithms and datasets designed to elicit particular behaviors, making it cr...
Current autoregressive Vision Language Models (VLMs) usually rely on a large number of visual tokens to represent images, resulting in a need for more compute e...
Machine Learning Interatomic Potentials (MLIPs) sometimes fail to reproduce the physical smoothness of the quantum potential energy surface (PES), leading to er...
From generating headlines to fabricating news, the Large Language Models (LLMs) are typically assessed by their final outputs, under the safety assumption that ...
Large language models often struggle to recognize their knowledge limits in closed-book question answering, leading to confident hallucinations. While decompose...
Linear attention offers a computationally efficient yet expressive alternative to softmax attention. However, recent empirical results indicate that the state o...
Pose and motion priors play a crucial role in humanoid robotics. Although such priors have been widely studied in human motion recovery (HMR) domain with a rang...
Quantum chemistry is a foundational enabling tool for the fields of chemistry, materials science, computational biology and others. Despite of its power, the pr...
We present El Agente Estructural, a multimodal, natural-language-driven geometry-generation and manipulation agent for autonomous chemistry and molecular modell...
Reasoning language models, which generate long chains of thought, dramatically outperform non-reasoning language models on abstract problems. However, the inter...
With the advancement of 3D scanning technologies, point clouds have become fundamental for representing 3D spatial data, with applications that span across vari...
Our theoretical understanding of neural networks is lagging behind their empirical success. One of the important unexplained phenomena is why and how, during th...
Software Engineering (SE) faces simultaneous pressure from AI automation (reducing code production costs) and hardware-energy constraints (amplifying failure co...
Statically-annotated types have been shown to aid developers in a number of programming tasks, and this benefit holds true even when static type checking is not...
Human nail diseases are gradually observed over all age groups, especially among older individuals, often going ignored until they become severe. Early detectio...
Accurate risk stratification of precancerous polyps during routine colonoscopy screenings is essential for lowering the risk of developing colorectal cancer (CR...
The rapid growth of large language models (LLMs) has outpaced the evolution of single-GPU hardware, making model scale increasingly constrained by memory capaci...
True self-evolution requires agents to act as lifelong learners that internalize novel experiences to solve future problems. However, rigorously measuring this ...
Omni-modal Large Language Models (Omni-LLMs) have demonstrated strong capabilities in audio-video understanding tasks. However, their reliance on long multimoda...
A controller -- a software module managing hardware behavior -- is a key component of a typical robot system. While control theory gives safety guarantees for s...
