MotionVLA: Vision-Language-Action Model for Humanoid Motion
Generating realistic humanoid motion from scene images and text involves both low-frequency pose semantics and high-frequency physical dynamics. However, many existing methods toke...
Research Papers
Latest AI/ML research from ArXiv and Papers with Code
Rethinking the Role of Efficient Attention in Hybrid Architectures
Modern language models increasingly adopt hybrid architectures that combine full attention with efficient attention modules, such as sliding-window attention (SWA) and recurrent se...
Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale
Efficient and scalable agentic intelligence requires models that can deliver both low-latency responses and strong reasoning capabilities while remaining practical to train, serve,...
RefGC-SR^2: Reference-guided Generated Content Super-Resolution and Refinement
Reference-guided generation (e.g., object compositing, customization) has progressed rapidly, yet current pipelines share a fundamental limitation: the object-centric high-resoluti...
ReSyn: A Generalized Recursive Regular Expression Synthesis Framework
Existing Programming-By-Example (PBE) systems often rely on simplified benchmarks that fail to capture the high structural complexity of real-world regexes, such as deeper nesting ...
CODA-BENCH: Can Code Agents Handle Data-Intensive Tasks?
Advanced agents are increasingly demonstrating the potential to operate as autonomous engineers, creating a growing demand for evaluation benchmarks that capture the complexity of ...
Beyond Scalar Distances: Semantic Attribute Gradients from Frozen MLLMs for Visual Embeddings
Vision encoders for retrieval are typically trained with class-label supervision: each training pair reduces to a scalar that uniformly pushes the embedding apart or pulls it toget...
DragMesh-2: Physically Plausible Dexterous Hand-Object Interaction with Articulated Objects
Dexterous interaction with articulated objects is important for household, assistive, and humanoid manipulation, where multi-finger hands can provide compliant contact patterns bey...
Beyond Monolingual Deep Research: Evaluating Agents and Retrievers with Cross-Lingual BrowseComp-Plus
Deep research agents are increasingly evaluated on their ability to search for evidence, reason over retrieved sources, and produce grounded answers. Existing browsing benchmarks, ...
Visual-Seeker: Towards Visual-Native Multimodal Agentic Search via Active Visual Reasoning
Multimodal large language models (MLLMs) have demonstrated impressive capabilities in many visual tasks, but they often struggle with factual grounding when confronted with complex...
IndustryBench-MIPU: Benchmarking Multi-Image Attribute Value Extraction for Industrial Products
Industrial products such as valves and circuit breakers are defined by dense technical specifications that govern procurement, compatibility, and safety across supply chains. These...
FastContext: Training Efficient Repository Explorer for Coding Agents
Large Language Model (LLM) coding agents have achieved strong results on software engineering tasks, yet repository exploration remains a major bottleneck: locating relevant code c...
ViT-Up: Faithful Feature Upsampling for Vision Transformers
Vision Transformers (ViTs) have become a dominant architecture for visual representation learning, providing exceptionally strong and broadly reusable backbone features. However, V...
Memento: Reconstruct to Remember for Consistent Long Video Generation
Long-form video generation requires recurring subjects to remain consistent across various shots, viewpoints, motions, and scene transitions. Existing temporal decomposition method...
RepFusion: Leveraging Multimodal Priors for Denoising in Representation Space
Large language models (LLMs) are widely used in text-to-image (T2I) systems, but they are typically limited to text encoding, while denoising is handled by newly trained generative...
LLM Agents Can See Code Repositories
Coding agents powered by large language models have demonstrated strong performance on software engineering tasks. Yet most agents consume repositories almost entirely as text, whi...
Hy-Embodied-0.5-VLA: From Vision-Language-Action Models to a Real-World Robot Learning Stack
In this report, we present Hy-Embodied-0.5-VLA, abbreviated as HyVLA-0.5, an end-to-end system that spans the full robot learning stack: data collection, model design, continued pr...
HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry
AI agent performance depends critically on the runtime harness, comprising the prompts, tools, memory, and control flow that mediate how a model observes, reasons, and acts. Yet to...
AFFORDANCE20Q: Evaluating Affordance Reasoning from Physical Properties
Affordance reasoning, the inference of an object's action possibilities from its physical properties (e.g., shape and material), is fundamental to human physical understanding and ...
Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
We introduce Nemotron 3 Ultra, a 550 billion total and 55 billion active parameter Mixture-of-Experts Hybrid Mamba-Attention language model. We pre-trained Nemotron 3 Ultra on 20 t...
Selective Control under Noisy Perception: Governance Failures Hidden by Aggregate Metrics in Modular Networks
A content-moderation system can score well on every standard accuracy metric and still cause real harm, if its mistakes fall on the few users who connect otherwise separate communi...
LoSoNA: A Benchmark for Local Social Norm Adaptation in Group Conversations
Online group chats are social spaces with local conversational norms that are rarely stated explicitly. The ability and willingness of LLM-based agents to recognize and adapt to th...
Squeeze-Release: Iterative Pruning with Exact Structural Minimization
Unstructured pruning produces sparse weight tensors, but the standard implementation keeps tensor shapes unchanged so the deployed model is no smaller than before pruning. We prese...
MVEB: Massive Video Embedding Benchmark
We introduce the Massive Video Embedding Benchmark (MVEB), a 23-task benchmark for video embeddings spanning classification, zero-shot classification, clustering, pair classificati...