RynnUnify: Towards Unified Embodied Brain
We introduce RynnUnify, a 16B unified embodied model that combines strong embodied understanding with long-horizon visual planning through interleaved video--language reasoning. Wi...
Papers
HoloBoxing: A Simple Recipe for Humanoid Boxing with 7 Minutes of Single-GPU Training
HoloBoxing presents a simple recipe for learning humanoid boxing by building on a pretrained whole-body controller. The recipe separates reusable motor skills from task decisions: ...
Can Test-Time Memory Evolution Outperform Test-Time Training for Scientific Discovery?
Recent test-time training (TTT) frameworks have enabled open-weight large language models (LLMs) to outperform inference-only frameworks powered by frontier models on scientific di...
Are Frontier VLM Agents Ready to Be Robot Generalists? An Empirical Study with the Embodied Agent Arena
A robot generalist must interpret a scene, act on it, and satisfy every condition of a task. How far do frontier vision-language models (VLMs) meet these demands? We introduce Embo...
Efficient Streaming Audio-Visual Target Speaker Extraction for Real-World Acoustic Scenes
Streaming audio-visual target speaker extraction (AVTSE) is essential for latency-sensitive applications. However, current causal systems face two coupled gaps. First, standard ben...
Sensorimotor Alignment: A Platonic Proxy for Embodied Policy Success
Robot foundation models are typically evaluated through costly closed-loop rollouts, motivating low-cost offline proxies for model capability. The Platonic Representation Hypothesi...
LoCA: Enabling Multi-Modality in Geospatial Location Encoders
Location encoders map geographic coordinates to high-dimensional descriptors through contrastive alignment with paired Earth Observation imagery. We prove that this construction is...
Rethinking Sequence Compression with Test-time Regression
Sequence compression is a fundamental operation and a critical information bottleneck in efficient language and multimodal models, and yet prevailing approaches based on pooling or...
GLOW-FM: Efficient Generative Low-Light Image Enhancement with One-Step Latent Flow Matching
Low-light image enhancement (LLIE) aims to recover well-exposed and perceptually faithful images from severely degraded observations. Recent diffusion-based generative methods achi...
Making MLLM Latents Matter: Factor-Aware Predictive Learning for Cinematic Video Generation
Cinematic video generation requires both temporal inference from limited inputs (i.e., sparse rather than frame-by-frame guidance) and factor-aware control of character, scene, act...
Inherited, Not Invented: Tracing the Provenance of Wait in Reasoning Models
Reinforcement learning (RL) is credited with teaching reasoning models to write {wait} before reconsidering a step, yet large RL accuracy gains do not require the word. This view c...
CellTrack-Bench: Microscopic Cell Tracking Benchmark for Vision-Language Models
Large language models have shown outstanding performance on text-first tasks such as coding, math, and writing. Recent efforts are shifting models' training to include scientific p...
Dual Exam: Controlled Evaluation of Multimodal Agents and World Models
World Models (WMs) can support Multimodal Agents (MAs) through simulated experience, while Agent trajectories can inform World Model refinement. Evaluating this interaction require...
On the Token Collapse Phenomenon in Textual Graph Soft Prompting
Recent methods for injecting graph structure into LLM prompts include graph soft prompting, in which a graph neural network (GNN) learns graph-specific tokens that capture relation...
HiSTEVE 1.0: Harnessing Human-Interface VLA Agents for Open-World Games
Building virtual embodied agents that operate in open-ended games like human players is a long-standing goal requiring both long-horizon autonomy and reliable native-interface cont...
PaperFormalizer: Author-in-the-Loop Autoformalization of Research Papers in Lean
Even a carefully proofread paper can leave small gaps in its proofs or its stated assumptions. We introduce PaperFormalizer, a Lean-based agentic pipeline that helps authors find a...
RIDAR: Safeguarding Research Integrity in Autonomous Research Agents via Automated Detection and Runtime Intervention
Autonomous research agents are increasingly used to automate large portions of scientific research, yet they are prone to research integrity violations (RIVs): behaviors that compr...
Different Tasks, Different Timesteps: Temporal Task-Aware Quantization for Diffusion Language Models
Diffusion Language Models (DLMs) introduce unique quantization challenges due to their iterative denoising process. In this work, we reveal that quantization sensitivity is both ta...
VibeGame: Prompt-to-Game Development with AI-Native Engine and Self-Evolving Adversarial Agent Team
Large language model agents have enabled software development through natural-language interaction, but extending this paradigm to end-to-end game development remains challenging. ...
Joint or Per-Option? Compact Encoders for Closed-Set Decisions from 17 Million to 1 Billion Parameters
Many language-model pipelines end in a closed-set decision, such as selecting a tool. Prompting a large language model for it is slow and order-sensitive. We ask how small an encod...
Reading, Writing, Sharing, and Interacting with the World through Video
Video foundation models have advanced rapidly in understanding and generating visual sequences, while video world models seek to capture the underlying dynamics of the world they d...
Every Weight Is a Path of Shared Discrete Decisions
We introduce TWIG (Tree-structured Weights with Inherited Gates), a representation in which every weight of a neural network is the end of a path of small discrete decisions: a sig...
FocusVLA: Future-Intent Guided Dynamic View Routing for Vision-Language-Action Models
Vision-language-action (VLA) models have become an important paradigm for robotic manipulation by unifying visual perception, language understanding, and action generation. Since r...
IQuest-Q1: Advancing Foundation Capabilities for Agentic CLI Systems
We present IQuest-Q1, a sparse Mixture-of-Experts (MoE) agentic foundation model with 320B total parameters (15B activated). IQuest-Q1 is developed through a three-stage process: (...