Video = World + Event Stream
We present Wan-Streamer v0.3, which reframes our native-streaming interaction model under a single organizing view: a video is a world plus an event stream. The world is the persis...
Papers
LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget
A growing gap separates inference context lengths from RL post-training: inference systems are approaching million-token contexts, while post-training workloads often remain at 256...
SUFLECA: Scaling Up Feature Learning for CAD-to-image Alignment
CAD-to-image alignment aims to estimate an object's 9D pose (rotation, translation, and anisotropic scale) from a single RGB image, enabling applications in robotics and augmented ...
RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources
Skills are a useful abstraction for software agents, turning human and agent experience into reusable procedural knowledge. Yet existing skill libraries are mostly hand-written, te...
Hierarchical Denoising For Multi-Step Visual Reasoning
Video models are evolving into vision foundation models, yet they still lack human-like multi-step reasoning. Streaming autoregressive diffusion models are efficient but limited in...
xHC: Expanded Hyper-Connections
Hyper-Connections (HC) expand the residual stream of Transformers into N parallel streams, providing a form of memory scaling beyond model width and depth. Manifold-Constrained HC ...
VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding
Recent advances in video understanding have spanned motion, long video, and streaming interaction, driving this field toward real-world applications. Despite this progress, current...
VIABench: A Comprehensive Video Benchmark Collected from Blind Individuals for Visual Impairment Assistance
Visually impaired individuals (VIIs) encounter significant daily challenges due to limited access to visual information. Although Multimodal Large Language Models (MLLMs) have achi...
Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectories
We present Xiaomi-Robotics-1, a foundational vision-language-action (VLA) model capable of (1) following diverse language instructions to perform a wide range of mobile manipulatio...
On-Policy Delta Distillation
On-policy distillation is an alternative post-training method in reinforcement learning that alleviates the constraints imposed by reward models by providing token-level supervisio...
Multi-Turn On-Policy Distillation with Prefix Replay
We study on-policy distillation (OPD) for agentic tasks, where an LLM agent interacts with an environment over multiple turns and a student imitates a teacher over these multi-turn...
Beyond Entropy: Correctness-Aware Advantage Shaping via Contrastive Policy Optimization
Reinforcement learning with verifiable rewards (RLVR) commonly uses entropy for advantage shaping. However, entropy cannot distinguish useful uncertainty from detrimental confusion...
AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities
As Large Language Models (LLMs) evolve into autonomous agents, the need for unified evaluation infrastructure becomes critical. However, current evaluation pipelines remain highly ...
GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearch
World Action Models (WAMs) improve robot policy learning by jointly modeling actions and future visual observations, using future scene evolution as dense supervision for physicall...
KnowAct-GUIClaw: Know Deeply, Act Perfectly, Personal GUI Assistant with Self-Evolving Memory and Skill
OpenClaw has emerged as a leading agent framework for complex task automation, yet it faces insufficient cross-platform GUI interaction support and a well-built self-evolution mech...
From Pixels to States: Rethinking Interactive World Models as Game Engines
Building interactive worlds that respond coherently to player actions has long been a shared goal of computer graphics, games, and artificial intelligence. Recent video generative ...
OvisOCR2 Technical Report
We introduce OvisOCR2, a 0.8B document parsing model. OvisOCR2 is designed as an end-to-end parser: given a document page image, it generates a Markdown representation in natural r...
Smarter and Cheaper at Once: Byte-Exact KV-Cache Grafting Turns a Frozen Small Model into a Verified-Knowledge Flywheel
We report a way to make a frozen small language model both more capable and dramatically cheaper at once, without changing any weights. Verified knowledge is deposited once as a by...
Multi-Head Latent Control: A Unified Interface for LLM Agent Decision Making
Large language models are increasingly deployed as agents, but reliable agentic behavior requires more than next-token prediction. At inference time, it is preferred that an agent ...
Cura 1T: Specialized Model for Agentic Healthcare
Healthcare spans high-stakes communication, expert reasoning, and workflow execution, yet specialized LLMs that cover these use cases together remain limited. A healthcare model mu...
Open-AoE: An Open Egocentric Manipulation Dataset and Toolchain for Embodied Learning
Egocentric videos of human manipulation provide scalable supervision for embodied intelligence, yet existing resources rarely combine low-cost continuous capture, manipulation-leve...
Diagnosing and Calibrating Tool-Call Boundary Drift in Multi-Teacher On-Policy Distillation
Agentic language models must learn when to call tools, when to consume tool responses, and when to answer directly. This makes multi-teacher on-policy distillation a natural traini...
RxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Imagination
Embodied cognition requires agents to connect high-level task reasoning with the physical states to be achieved. We introduce Hy-Embodied-RxBrain, an embodied cognition foundation ...
Hallo4D: Multi-Modal Hallucination Mitigation for Consistent Spatio-Temporal Generation
While recent advances in 3D generation have enabled impressive visual synthesis, existing methods often rely on 2D diffusion supervision without explicit mechanisms for geometric c...