MMAE: A Massive Multitask Audio Editing Benchmark
We introduce MMAE, a Massive Multitask Audio Editing benchmark, serving as the first comprehensive evaluation testbed designed for general-purpose instruction-based audio editing. ...
Research Papers
Latest AI/ML research from ArXiv and Papers with Code
Stream3D-VLM: Online 3D Spatial Understanding with Incremental Geometry Priors
Despite advances in 3D scene understanding, existing 3D Large Multimodal Models operate in offline settings, requiring complete scene observations or predefined video clips. In thi...
DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded Reasoning
Deep Research (DR) has emerged as a new agentic paradigm to tackle complex, open-ended research tasks, demanding systems that can iteratively frame problems, acquire evidence, veri...
Robotic Policy Adaptation via Weight-Space Meta-Learning
Vision-Language-Action (VLA) models are emerging as a promising paradigm for robotic manipulation, enabling general-purpose policies trained from large corpora of demonstrations an...
Streaming Video Generation with Streaming Force Control
We introduce StreamForce, a streaming video generation framework that enables physically grounded control through continuous force inputs. Unlike prior video models that train sepa...
AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization
Despite being a pivotal frontier, interactive world modeling remains underexplored in terms of the versatile controllability required by practical scenarios. To bridge this gap, we...
UniSHARP: Universal Sharp Monocular View Synthesis
In this work, we focus on extending SHARP, the popular photorealistic view synthesis method, for universal monocular rendering across a continuum of camera systems, from convention...
Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills
LLM-driven software engineering agents have become a central testbed for real-world language-model capability, yet their training remains limited by the availability of high-qualit...
dots.tts Technical Report
We present dots.tts, a 2B-parameter continuous autoregressive text-to-speech (TTS) foundation model that models speech in a continuous latent space. Compared with existing continuo...
Empirical Study on the Characteristics and Evolution of AI-usage in GitHub Repositories: Evidence from Code Comments
Developers increasingly use AI tools such as ChatGPT, Copilot, and Claude in everyday software workflows, but prior studies often evaluate LLM outputs in isolation rather than exam...
The Cold-Start Safety Gap in LLM Agents
Are tool-calling LLM agents equally safe throughout a conversation? We discover they are not: agents are most vulnerable at the very start of a session and become substantially saf...
TBD-VLA: Temporal Block Diffusion Vision Language Action Model
Discrete Vision-Language-Action (VLA) models typically formulate action generation as next-token prediction over discretized action spaces, conditioning each token autoregressively...
Towards Retrieving Interaction Spaces for Agentic Search
Retrieval for search agents is still inherited from non-agentic information retrieval: a retriever ranks the corpus and the agent reads a small set of returned documents. Recent di...
SlimSearcher: Training Efficiency-Aware Web Agents via Adaptive Reward Gating
Deep research agents have demonstrated remarkable capabilities in complex information-seeking tasks, yet this power comes at a steep computational cost. Driven by accuracy-focused ...
MemDreamer: Decoupling Perception and Reasoning for Long Video Understanding via Hierarchical Graph Memory and Agentic Retrieval Mechanism
Current Vision-Language Models struggle with hours-long videos because processing full-length visual sequences induces prohibitive token explosion and attention dilution. To overco...
Entropy as a Structural Prior: How a Log-Barrier on DiT Belief Space Drives Musical Diversity and Development
Confidence-based loss weighting is usually avoided in generative models because it accelerates errors when the model is confidently wrong, but this intuition breaks down in supervi...
LIMMT: Less is More for Motion Tracking
We argue that high-quality motion data can steer tracking policies toward better optimization trajectories early in training. In this work, we introduce LIMMT (Less Is More for Mot...
Your UnEmbedding Matrix is Secretly a Feature Lens for Text Embeddings
Large language models exhibit impressive zero-shot capabilities across a wide range of downstream tasks. However, they struggle to function as off-the-shelf embedding models, leadi...
PaperFlow: Profiling, Recommending, and Adapting Across Daily Paper Streams
Scientific paper recommendation is typically evaluated as static ranking over a fixed candidate set, yet real scientific reading unfolds as a daily, longitudinal process in which i...
Watch, Remember, Reason: Human-View Video Understanding with MLLMs
Video understanding is being rapidly transformed by multimodal large language models (MLLMs), as research moves from short clips to long, multimodal, and knowledge-intensive video ...
StepPO: Step-Aligned Policy Optimization for Agentic Reinforcement Learning
Agentic reinforcement learning (RL) is emerging as a critical post-training paradigm for improving LLM agent capabilities. Existing RL algorithms for LLMs largely follow the token-...
On the Geometry of On-Policy Distillation
On-policy distillation (OPD) is increasingly used to improve large language model reasoning, but its training dynamics remain poorly understood. We characterize the trajectory of O...
Struct-Searcher: Agentic Structural Thinking Advances Multimodal Deep Information Seeking
Deep research agents have attracted increasing attention for their ability to collect large-scale online information to acquire target knowledge, with recent efforts shifting from ...
SWE-Explore: Benchmarking How Coding Agents Explore Repositories
Repository-level coding benchmarks such as SWE-bench have driven a rapid surge in the capabilities of coding agents. Yet they usually treat coding tasks as a holistic, binary predi...