Despite advances in 3D scene understanding, existing 3D Large Multimodal Models operate in offline settings, requiring complete scene observations or predefined video clips. In thi...
Deep Research (DR) has emerged as a new agentic paradigm to tackle complex, open-ended research tasks, demanding systems that can iteratively frame problems, acquire evidence, veri...
Vision-Language-Action (VLA) models are emerging as a promising paradigm for robotic manipulation, enabling general-purpose policies trained from large corpora of demonstrations an...
We introduce StreamForce, a streaming video generation framework that enables physically grounded control through continuous force inputs. Unlike prior video models that train sepa...
Despite being a pivotal frontier, interactive world modeling remains underexplored in terms of the versatile controllability required by practical scenarios. To bridge this gap, we...
In this work, we focus on extending SHARP, the popular photorealistic view synthesis method, for universal monocular rendering across a continuum of camera systems, from convention...
LLM-driven software engineering agents have become a central testbed for real-world language-model capability, yet their training remains limited by the availability of high-qualit...
We present dots.tts, a 2B-parameter continuous autoregressive text-to-speech (TTS) foundation model that models speech in a continuous latent space. Compared with existing continuo...
Developers increasingly use AI tools such as ChatGPT, Copilot, and Claude in everyday software workflows, but prior studies often evaluate LLM outputs in isolation rather than exam...
Are tool-calling LLM agents equally safe throughout a conversation? We discover they are not: agents are most vulnerable at the very start of a session and become substantially saf...
Discrete Vision-Language-Action (VLA) models typically formulate action generation as next-token prediction over discretized action spaces, conditioning each token autoregressively...
Retrieval for search agents is still inherited from non-agentic information retrieval: a retriever ranks the corpus and the agent reads a small set of returned documents. Recent di...
Deep research agents have demonstrated remarkable capabilities in complex information-seeking tasks, yet this power comes at a steep computational cost. Driven by accuracy-focused ...
Current Vision-Language Models struggle with hours-long videos because processing full-length visual sequences induces prohibitive token explosion and attention dilution. To overco...
Confidence-based loss weighting is usually avoided in generative models because it accelerates errors when the model is confidently wrong, but this intuition breaks down in supervi...
We argue that high-quality motion data can steer tracking policies toward better optimization trajectories early in training. In this work, we introduce LIMMT (Less Is More for Mot...
Large language models exhibit impressive zero-shot capabilities across a wide range of downstream tasks. However, they struggle to function as off-the-shelf embedding models, leadi...
Scientific paper recommendation is typically evaluated as static ranking over a fixed candidate set, yet real scientific reading unfolds as a daily, longitudinal process in which i...
Video understanding is being rapidly transformed by multimodal large language models (MLLMs), as research moves from short clips to long, multimodal, and knowledge-intensive video ...
On-policy distillation (OPD) is increasingly used to improve large language model reasoning, but its training dynamics remain poorly understood. We characterize the trajectory of O...
Deep research agents have attracted increasing attention for their ability to collect large-scale online information to acquire target knowledge, with recent efforts shifting from ...
Repository-level coding benchmarks such as SWE-bench have driven a rapid surge in the capabilities of coding agents. Yet they usually treat coding tasks as a holistic, binary predi...
Harmony is a compact symbolic layer where mathematical pitch relations, acoustic consonance, and musical convention meet. This report treats chord-symbol sequences not as a complet...
Pipeline parallelism is essential for training large neural networks, but existing schedules trade off throughput, memory, and optimization consistency. Synchronous pipelines prese...