Wasserstein gradient flows for Coulomb discrepancies
arXiv:2607.12579v1 Announce Type: cross Abstract: We study the long-time behavior of the Wasserstein gradient flow of the squared Maximum Mean Discrepancy (MMD) between a probability measure…
Papers 5625 stories
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 physically grounded…
PolicyShiftGuard: Benchmarking and Improving Policy-Adaptive Image Guardrails
Image guardrails are typically trained and evaluated under a fixed safety policy, implicitly treating safety as an intrinsic property of an image. Real deployments are different:…
ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation
Structured pruning is a hardware-friendly way to compress LLMs, but it is mostly validated on multiple-choice recognition tasks, while the same compressed checkpoints can collapse on…
Ring-Zero: Scaling Zero RL to a Trillion Parameters for Emergent Reasoning
Reinforcement learning with verifiable rewards without human-annotated data, often referred to as zero RL, has emerged as a powerful paradigm for eliciting chain-of-thought reasoning. However, due…
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 mechanism. These…
Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable
The capability of a modern AI agent depends not only on its foundation model but also on its harness, which constructs prompts, manages state, invokes tools,…
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…
MAGIC: Transition-Aware Generation of Navigable Multi-Scene Game Worlds with Large Language Models
Multi-scene navigation (clearing an objective in one bounded space and then crossing a portal into the next) is a defining feature of contemporary 3D games, but…
Are LLMs Ready for Scientific Discovery? A Capability-Oriented Benchmark for AI Scientists
Existing benchmarks for scientific data analysis evaluate LLMs primarily on code execution or workflow completion, overlooking that scientific analysis serves to support distinct types of scientific…
Navigating the Mirage: A Dual-Path Agentic Framework for Robust Misleading Chart Question Answering
Despite the success of Vision-Language Models (VLMs), misleading charts remain a significant challenge due to their deceptive visual structures and distorted data representations. We present ChartCynics,…
Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models
Coding agents must integrate external tool returns into ongoing reasoning - a capability that standard left-to-right pretraining on code exposes only in its forward direction. We…
What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness
Large language models fine-tuned for forecasting can be accurate yet poorly calibrated, and their chain-of-thought (CoT) reasoning may not faithfully reflect the evidence behind a forecast.…
SynthDocBench: Controlled Benchmark for Long-Context Visual Document Understanding
Vision language models (VLMs) have achieved strong performance on visual document understanding benchmarks such as DocVQA, ChartQA, and MMLongBench-Doc. However, real-world documents combine multiple factors such…
Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation
Visual generators excel at rendering, but they confidently fabricate what they do not know. User requests are unbounded, evolving, and deeply long-tailed: new characters, trending entities,…
MonkeyOCRv2: A Visual-Text Foundation Model for Document AI
Mainstream visual encoders are pretrained on natural images and cannot be effectively applied to document images without document-oriented adaptation, as dense text and fine-grained character strokes…
Let RGB Be the Language of Vision
This work introduces a unified formulation for vision models, where diverse forms of visual information beyond natural images, such as masks, depth maps, and other structured…
MuScriptor: An Open Model for Multi-Instrument Music Transcription
Existing methods for automatic music transcription are often limited to single-instrument recordings or fail on complex, real music mixes. Although previous work utilizes synthetic training data,…
Towards Autonomous and Auditable Medical Imaging Model Development
Large language model (LLM) agents are beginning to automate machine learning engineering (MLE) by coupling planning, code execution, debugging, and empirical feedback. Translating this capability to…
Principled Analysis of Deep Reinforcement Learning Evaluation and Design Paradigms
Starting from the utilization of deep neural networks to approximate the state-action value function that led to winning one of the most challenging games, to algorithmic…
Blind-Spots-Bench: Evaluating Blind Spots in Multimodal Models
Modern AI models achieve strong performance on many established benchmarks, yet they still fail on tasks that humans find almost trivial, such as manipulating a string…
Optimization Is Not All You Need
arXiv:2607.11977v1 Announce Type: new Abstract: In 2019, OpenAI released two million GPT-2 outputs-ungrammatical, half broken-to aid the detection of machine-generated text. The alignment that produced their…
On-Device Deep Research at 4B: Exposure Bounds Faithfulness, Retrieval Bounds Coverage
arXiv:2607.12257v1 Announce Type: cross Abstract: On-device research agents search a corpus, read sources, and write a cited brief on a personal laptop. Whether their citations are…
Hybrid Continual Learning for Low-Resource Australian Aboriginal Language Identification
arXiv:2607.11946v1 Announce Type: new Abstract: Language identification is an important step toward integrating endangered Australian Aboriginal languages (AALs) into speech technologies supporting language revitalisation and digital…