Modern diffusion/flow-based models for image generation typically exhibit two core characteristics: (i) using multi-step sampling, and (ii) operating in a laten...
Public repositories host millions of fine-tuned models, yet community usage remains disproportionately concentrated on a small number of foundation checkpoints....
Hybrid Transformer architectures, which combine softmax attention blocks and recurrent neural networks (RNNs), have shown a desirable performance-throughput tra...
Agentic Reinforcement Learning (Agentic RL) has achieved notable success in enabling agents to perform complex reasoning and tool use. However, most methods sti...
We introduce UEval, a benchmark to evaluate unified models, i.e., models capable of generating both images and text. UEval comprises 1,000 expert-curated questi...
Manipulating dynamic objects remains an open challenge for Vision-Language-Action (VLA) models, which, despite strong generalization in static manipulation, str...
Neural networks have been successfully applied in various resource-constrained edge devices, where usually central processing units (CPUs) instead of graphics p...
Large Vision-Language Models (VLMs) often answer classic visual illusions 'correctly' on original images, yet persist with the same responses when illusion fact...
The development of autonomous web agents, powered by Large Language Models (LLMs) and reinforcement learning (RL), represents a significant step towards general...
Due to limited supervised training data, large language models (LLMs) are typically pre-trained via a self-supervised 'predict the next word' objective on a vas...
Audio-Visual Foundation Models, which are pretrained to jointly generate sound and visual content, have recently shown an unprecedented ability to model multi-m...
In pruning, the Lottery Ticket Hypothesis posits that large networks contain sparse subnetworks, or winning tickets, that can be trained in isolation to match t...
Reasoning-oriented Large Language Models (LLMs) have achieved remarkable progress with Chain-of-Thought (CoT) prompting, yet they remain fundamentally limited b...
Matrix functions such as square root, inverse roots, and orthogonalization play a central role in preconditioned gradient methods for neural network training. T...
Existing agent safety benchmarks report binary accuracy, conflating early intervention with post-mortem analysis. A detector that flags a violation at step 8 en...
Full-image relighting remains a challenging problem due to the difficulty of collecting large-scale structured paired data, the difficulty of maintaining physic...
Pancreatic ductal adenocarcinoma (PDAC), one of the deadliest solid malignancies, is often detected at a late and inoperable stage. Retrospective reviews of pre...
Large Language Models (LLMs) deliver state-of-the-art performance on complex reasoning tasks, but their inference costs limit deployment at scale. Small Languag...
Multi-objective optimization aims to solve problems with competing objectives, often with only black-box access to a problem and a limited budget of measurement...
Frontier large language models (LLMs) excel as autonomous agents in many domains, yet they remain untested in complex enterprise systems where hidden workflows ...
Test-time scaling has been widely adopted to enhance the capabilities of Large Language Model (LLM) agents in software engineering (SWE) tasks. However, the sta...
Current generative video models excel at producing novel content from text and image prompts, but leave a critical gap in editing existing pre-recorded videos, ...
Creative image generation has emerged as a compelling area of research, driven by the need to produce novel and high-quality images that expand the boundaries o...
Large language models (LLMs) have demonstrated strong performance on medical benchmarks, including question answering and diagnosis. To enable their use in clin...
