Multi-turn image editing aims to modify an image according to a sequence of instructions, enabling more effective interactive visual content creation for users. However, existing m...
Neural simulation of high-fidelity deformable bodies is a foundational challenge in computer graphics and physical AI. Long-horizon prediction for high-resolution 3D volumetric mes...
Flow-matching vision-language-action (VLA) models generate an action chunk by iteratively denoising Gaussian noise, but typically execute only a short prefix before replanning with...
Test-time scaling (TTS) improves large language model (LLM) reasoning by sampling multiple answers, but fixed sampling budgets ignore both query difficulty and the changing energy ...
Feed-forward 3D Gaussian Splatting (3DGS) promises instant scene reconstruction with high-quality novel-view synthesis. Yet, fine-grained geometry and appearance remain difficult t...
AI coworkers must coordinate tools, communicate across turns, and act on changing workspace state while respecting workflow constraints. Constructing training experience for these ...
Digital art generation has undergone a massive paradigm shift, moving from static image synthesis to dynamic video generation that can mimic the human painting process. While exist...
Model--harness co-evolution has emerged as a prominent paradigm for recursive self-improving (RSI) agents, jointly evolving their execution scaffolds and intrinsic capabilities. We...
Speech anonymization has focused on the acoustic signal, leaving open how much speaker information the transcribed words themselves retain. In this work, we study pairwise speaker ...
Video Reasoning Segmentation (VRS) requires a model to identify an implicitly described target and predict its pixel-level mask trajectory, while resolving the spatial relations an...
As multimodal resources are transformed into media outputs, agentic AI is expected to stay aligned with design intent over long horizons. Designers follow briefs specifying goals, ...
While LLM-based agent systems have demonstrated remarkable proficiency in reasoning and solving complex real-world tasks, they also come with substantial token consumption and infe...
High-quality image editing requires precise modification of target regions while preserving the content of unrelated regions. Existing editing models produce flattened outputs that...
Structured knowledge retrieval acquires task-relevant evidence from structured knowledge sources for downstream tasks. Existing methods rely on unconstrained retrieval or predefine...
Evaluating software agents on a full benchmark is expensive. A small task subset can preserve agent rankings while yielding inaccurate scores. Historical responses provide useful s...
Effective test-time personalization requires LLM agents to adapt to query-dependent user preferences from lightweight interaction. We study persona selection with binary comparison...
Improving every agent in an LLM-based multi-agent system can be prohibitively costly, making it important to identify which agent should be prioritized to achieve the greatest syst...
Recent research-level physics-reasoning benchmarks for LLMs reveal a failure mode that lies not in knowledge or execution, but in modeling the world being reasoned about. Models of...
Recent works show that LLMs can generate kernels with strong performance on server GPUs. Edge deployment presents distinct challenges because the hardware is heterogeneous, the sof...
While LLM agents are increasingly capable of gathering and synthesizing evidence from a single homogeneous source, such as structured tables or unstructured data, real-world analyt...
We introduce avatar referring segmentation, which selects regions of animatable Gaussian avatars from language queries. A query can also specify a pose or motion to select matching...
Recent advances in general-purpose AI models and agentic systems have enabled them to perform some CAD tasks. A systematic assessment is now needed to establish what these systems ...
Unified audio-video creation requires a single model capable of text-conditioned joint synthesis, bidirectional cross-modal generation, and instruction-guided editing across both m...
Existing Multi-token prediction (MTP) methods are auxiliary by design: the multi-horizon loss mostly trains modules attached to the backbone, and each added horizon costs another m...