Do Thinking Tokens Help with Safety?
Today's reasoning models use thinking tokens to attain stronger performance on benchmarks than their instruction-tuned counterparts. It is also generally believed that this more "d...
Research Papers
Latest AI/ML research from ArXiv and Papers with Code
Trimming the Long-Tail of Visual World Modeling Evaluation
Physical interactions follow a long-tailed distribution: a set of common and regular interactions dominates human experience and visual data, while a broad spectrum of rare and irr...
Are We Ready For An Agent-Native Memory System?
Memory for large language model (LLM) agents has rapidly evolved from simple retrieval-augmented mechanisms into a data management system that supports persistent information stora...
Qwen-AgentWorld: Language World Models for General Agents
A world model predicts environment dynamics based on current observations and actions, serving as a core cognitive mechanism for reasoning and planning. In this work, we investigat...
OpenThoughts-Agent: Data Recipes for Agentic Models
Agentic language models dramatically expand the applications of AI yet little is publicly known about how to curate training data for broadly capable agents. Existing open efforts ...
FLUX3D: High-Fidelity 3D Gaussian Generation with Diffusion-Aligned Sparse Representation
Sparse voxel representation has emerged as a scalable foundation for image-to-3D Gaussian Splatting (3DGS) generation, yet current methods struggle to preserve high-frequency visua...
What Intermediate Layers Know: Detecting Jailbreaks from Entropy Dynamics
Jailbreak attacks reveal a persistent weakness in aligned Large Language Models: carefully crafted prompts can elicit policy-violating responses despite safety training. While most...
DiffusionBench: On Holistic Evaluation of Diffusion Transformers
Diffusion transformer (DiT) research on image generation has converged to a single evaluation setup: class-conditional generation on ImageNet. While methods improve the FID and rel...
CAVEWOMAN: How Large Language Models Behave Under Linguistic Input and Output Compression
"Talk short. Drop grammar. Save token." This caveman style is widely promoted as a way to cut inference cost, but whether it actually saves anything depends on which channel (the u...
SkillHone: A Harness for Continual Agent Skill Evolution Through Persistent Decision History
Agent skills extend language-model agents with task-specific procedures, scripts, and references, but the tasks and environments they target continually change. Existing methods im...
IV-CoT: Implicit Visual Chain-of-Thought for Structure-Aware Text-to-Image Generation
Unified multi-modal large language models (MLLMs) have achieved strong text-to-image generation quality, but still struggle with structure-aware prompt following, where object coun...
Advancing WordArt-Oriented Scene Text Recognition: Datasets and Methods
WordArt (artistic text) features highly customized fonts, textures, and layouts, making WordArt-oriented scene TExt Recognition (WATER) substantially more challenging than general ...
Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models
We present Wan-Streamer, a native-streaming, end-to-end interactive foundation model designed from the ground up for real-time, low-latency, full-duplex audio-visual interaction. W...
Lite Any Stereo V2: Faster and Stronger Efficient Zero-Shot Stereo Matching
Recent advances in stereo matching have achieved remarkable accuracy, but often rely on large models, heavy computation, or additional foundation-model priors, making them difficul...
AsyncOPD: How Stale Can On-Policy Distillation Be?
On-policy distillation (OPD) trains a student on its own rollouts guided by teacher feedback and is becoming increasingly important for large language model (LLM) post-training. Li...
AGORA: An Archive-Grounded Benchmark for Agentic Workplace Document Reasoning
Large language models are increasingly deployed as agents that reason over documents rather than answer from parametric knowledge. We study archive-grounded reasoning: locating spa...
Transition-Aware best-of-N sampling for Longitudinal Chest X-ray Reports
In longitudinal clinical practice, every chest X-ray is read in the context of the patients prior exam, and much of what the radiologist communicates is the change from one visit t...
NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers?
We introduce NatureBench, a cross-discipline benchmark of 90 tasks distilled from peer-reviewed Nature-family publications, designed to evaluate whether AI coding agents can move b...
DREAM: Dense Retrieval Embeddings via Autoregressive Modeling
Dense retrieval embedding models are a fundamental component of modern retrieval-based AI systems. Most dense retrievers are trained with contrastive objectives, which require labe...
FLAT: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene Generation
Generating explorable 3D scenes from a single image requires strong generative priors and accurate geometric representations suitable for downstream use. Current video diffusion mo...
Thinking While Speaking: Inference-Time Knowledge Transfer for Responsive and Intelligent Conversational Voice Agents
Voice agents face a fundamental tension: the reasoning, retrieval, and tool use that make foundation models capable are iterative and slow, while conversational interaction demands...
ReMMD: Realistic Multilingual Multi-Image Agentic Verification for Multimodal Misinformation Detection
Multimodal misinformation detection is increasingly important because viral posts now combine long multilingual narratives, several images, mixed provenance, and subtle text--image...
Holistic Data Scheduler for LLM Pre-training via Multi-Objective Reinforcement Learning
The composition of training data, governed by the diversity of sources and their mixing strategy, is a cornerstone of Large Language Model (LLM) pre-training. Online Data Mixing (O...
Are Text-to-Image Models Inductivist Turkeys? A Counterfactual Benchmark for Causal Reasoning
Text-to-image (T2I) generation models have achieved remarkable progress in producing visually realistic images from natural language prompts. Yet it remains unclear whether their s...