WeVisOne-VL: Unified Visual Perception from Objects to Pixels
Existing vision-language models (VLMs) remain unreliable for fine-grained visual perception. In this report, we present WeVisOne-VL (WeChat Vision All-in-One), a powerful VLM that ...
Papers
MMVistaReason: Toward Open-Data and Post-Training Recipes for Multimodal Reasoning
Open multimodal reasoning models have benefited from large-scale reasoning supervision, yet reliable post-training remains challenging due to uneven data quality, inefficient super...
DISC: Domain-Integrated Similarity Cost for Time-Series Dataset
The growth of time-series datasets and foundation models has made dataset comparison a central part of time-series workflows. Assessing source-target transfer before model adaptati...
FilmFlow: Agentic System for 3D Virtual Film Cinematography
Complex camera motion is central to visual storytelling, yet translating cinematographic intent into controllable, executable camera trajectories remains challenging. We introduce ...
HiP3R: Hierarchical Pose Graphs for Long-Horizon 3D Reconstruction
Feed-forward models accurately estimate camera motion and 3D geometry from short video windows. However, computational and memory costs prevent direct inference on sequences contai...
Nested Sparsity for Scalable Pretraining and Continual Learning
Mixture-of-experts (MoE) transformers, the standard backbone for modern large-scale deep learning, employ conditional computation: only a sparse subset of model weights is used in ...
FLORA: An Open Model Suite for Scaling Robotics Data Engines
The life-cycle of robotics foundation models crucially depends on data labels. Outcome reward labels are needed for monitoring real-world deployments. Process reward labels are nee...
Is Complex Agentic Memory Always Needed? Naive RAG Is Stronger Than We Thought
LLM memory is widely used in long-term conversation understanding. Agentic memory systems often use mutation, structural organization, learned retrieval strategies, or other comple...
Skeleton-Grounded Latent Action Model for Robot World Models
Robot world models simulate how environments evolve in response to robot actions. Latent action models enable learning dynamics from videos by encoding visual transitions as proxy ...
R^2Orch: Recursive Self-Improvement for Agent Orchestration via Self-Play within a Skill-Internalization Loop
In recent years, agentic orchestration has been widely applied to solve complex human tasks. However, existing orchestration learning still faces key challenges, including hand-des...
Beyond Watching and Searching: Benchmarking Agents for Video-centered Deep Research Reports
Deep research agents synthesize open-web evidence into long reports, but current benchmarks do not evaluate research centered on a source video. We introduce Video-Centered Deep Re...
SCOPE: Compiling Natural-Language Policies into Neurosymbolic Predicate Programs
Policy enforcement for LLM agents has shifted from single-turn content moderation to compound, application-specific policies evaluated over multi-turn transcripts and tool-call tra...
Echo: Coupled Action and Task Status Signal Denoising for Vision Language Action Models
Recognizing task completion and failure enables robots to stop upon success and initiate recovery or replanning after failure. Existing methods augment Vision Language Action (VLA)...
Speculative Diffusion is a Tale of Two Tradeoffs
Speculative decoding is a technique that accelerates the inference speed of autoregressive large language models (LLMs) by sampling from a faster, lower quality draft model. Tradit...
UserArena: Benchmarking Interactive User Simulation for Long-Horizon Shopping Agents
Agentic recommendation pursues shopper goals through sequences of context-dependent decisions. Developing and evaluating such policies requires faithful recommendation world models...
DirCast: Live Esports Directing and Commentary with a Single Streaming Video-Language Model
A live esports broadcast needs a director who chooses which camera goes on air and a caster who talks over that choice, every second and without knowing what comes next. Streaming ...
Sub-monolayer tracking of molecular states at buried interfaces
Phenomena responsible for emerging technologies originate from novel molecular states at buried interfaces. Yet quantitatively resolving these features is out of reach in most case...
Extreme Compression of Per-Layer Embeddings via Cross-Layer Latent Vector Quantization
Scaling embedding capacity alongside Transformer computation is an emerging trend in language models. This trend makes high compression rates increasingly useful. Hence, we study e...
BrickWright: Agentic Creation of Physically Feasible Brick Builds
Frontier coding agents are becoming increasingly adept at 3D modeling. Yet, they still face challenges when building objects meant to be assembled in the physical world, often crea...
What Makes a Good Unmasking Policy? A Controlled Study of Learned Unmasking in Diffusion Language Models
Masked diffusion language models generate tokens in parallel, but their efficiency depends on which predictions are committed. Learned unmasking policies improve the speed--accurac...
DraMaze: A Multi-Agent Pipeline with Future-Aware Memory for Diverse Microdrama Script Generation
The rapid growth of microdramas has increased demand for high-quality script production. Long-form microdrama script generation with LLMs requires both diverse plot progression and...
Does LeWorldModel Preserve Local Action Geometry?
We examine how closely pretrained LeWorldModel (LeWM) reproduces the effects of small action changes. Using matched simulator and model responses, we measure action sensitivity wit...
F2G-Pose: Geometry-Aware Foundation Feature Lifting for Direct RGB-D Category-Level Object Pose Estimation
This paper studies category-level RGB-D object pose estimation, which recovers an object's 3D rotation and translation without instance-specific CAD models or reference views. This...
AnyGameRenderer: Entity-Consistent Generative Rendering Across Games and an Entity-Level Benchmark
AI coding agents can now build small playable games in minutes, but the results usually look like programmer art: gray blockouts, colored geometric primitives, and flat semantic bl...