Masked Visual Actions for Unified World Modeling
Video models absorb rich priors over how the visual world moves, interacts, and responds to contact, making them promising substrates for robotic world modeling. The central challe...
Research Papers
Latest AI/ML research from ArXiv and Papers with Code
Appearance Pointers -- Multimodal Region Control of Diffusion Transformers
Controllable image generation remains challenging for creative professionals, who often require precise regional control over materials, object identities, and spatial arrangements...
H^2SD: Hybrid Hindsight Self-Distillation
Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning capabilities of large language models on tasks such as mathematical reasoning and cod...
NexForge: Scaling Agent Capabilities through Requirement-Driven Task Synthesis for LLMs
Scaling executable agent training data for LLM post-training is bottlenecked by substrate-bound methods that tie task generation to predefined tools, repositories, or skill graphs:...
Moving Alphabet: A Controlled Study of Training Data for Text-to-Video Generation
Text-to-video generation has advanced significantly over the past five years through scaling of model size, data, and compute. Unlike model architecture, training data is often und...
FinanceComplexQA: Benchmarking Agentic Reasoning on Industrial-grade Financial Documents
Agentic Reasoning has become a transformative force in financial analysis due to its ability to integrate large-scale information and generate reliable and accurate content. Howeve...
AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents
LLM agent failures are difficult to debug because the step where an error surfaces is often not the one that caused it. Existing observability tools replay execution traces but pro...
Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers
Text-to-image diffusion transformers (DiTs) jointly process text and image tokens, yet their internal computation during denoising remains poorly understood. We introduce a causal ...
Scaling Laws for Hypernetwork-Based Knowledge Injection in Large Language Models
Injecting factual knowledge into large language models (LLMs) reliably and at scale remains an open challenge. Hypernetworks provide a promising solution to large-scale knowledge i...
Delineate Anything v2: A Global Foundation Model for Field Delineation
Accurate agricultural field boundary delineation at large scale is a foundational task for food security, supply chain transparency, and carbon accounting. While vision foundation ...
Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing
Large-scale visual generators are increasingly capable but costly to train, fine-tune, and deploy. We introduce Mage-Flow, a compact 4B-scale generative stack for efficient text-to...
Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing
Modern ASR models trained on heterogeneously annotated data treat transcription style (verbatim vs. intended) as an uncontrolled latent variable, causing measurable decoding instab...
AlayaWorld: Interactive Long-Horizon World Modeling -- Full Technical Report
Unlike conventional video game development, which relies on labor-intensive pipelines for asset production, animation, physics, and programming, video world models generate interac...
SLAM in Low-Light Environments: Project Report
Simultaneous localization and mapping (SLAM) is one of the fundamental problems in robotics, as it enables autonomous operations in real-world scenarios. Under low illumination, re...
SWE-Pruner Pro: The Coder LLM Already Knows What to Prune
Pruning long context for coding agents has been a vital technology for efficient context management. While existing context pruning methods such as SWE-Pruner realize this by attac...
RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model
We present RynnBrain 1.1, a family of embodied foundation models spanning 2B, 9B, and 122B-A10B scales. Trained with a unified spatio-temporal and physically grounded framework, Ry...
LLM-as-a-Coach: Experiential Learning for Non-Verifiable Tasks
Reinforcement learning (RL) on open-ended tasks compresses an LLM's rubric-based evaluation into a scalar reward, discarding rich textual feedback and conflating responses with dis...
DiFA: Inference-Time Forward-Process Alignment for Diffusion Models
The prevailing inference framework for diffusion models formulates generation fundamentally as a problem of numerical integration. This perspective casts the model as an exact esti...
Uncovering Latent Reasoning Strategies in Language Models
A language model p_θ(y mid x) trained on reasoning tasks learns to solve problems via multiple distinct strategies, yet these strategies are implicit and entangled within the model...
EduPanel: A Three-Agent LLM Judge for Teaching Videos -- Reliability, Complementarity, and Human Trust Calibration
Teaching videos are becoming a major medium for education, creating a growing need for scalable evaluation of their pedagogical quality. Existing automatic judges do not fully addr...
Subliminal Clocks: Latent Time Modelling in Diffusion Language Models
Diffusion Language Models (DLMs) have recently emerged as a promising alternative to autoregressive models. Unlike standard diffusion-based approaches, DLMs are not explicitly cond...
O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning
Industrial Video Anomaly Detection (IVAD) aims to identify anomalous objects and events in an industrial process, which is crucial for modern manufacturing and quality control syst...
Three-Body Scattering for Generative Modeling
Modern generative models typically rely on an adversarial critic, a prescribed noise-to-data path, or an autoregressive factorization. Instead, we show that a proper distributional...
HOMIE: Human-object Centric Video Personalization via Multimodal Intelligent Enchancement
Human-object centric video personalization (HOCVP) is a core task within subject-driven video generation. However, existing methods suffer from two key limitations. First, most app...