Latest AI/ML research from ArXiv and Papers with Code
The Frechet Inception Distance (FID) is the de facto arbiter of image generation, yet most papers report just a single number from a single trained model using a single sampling se...
Filmmaking demands precise motion control and reference image compositing -- capabilities that existing methods treat separately. Point-track-conditioned image-to-video models rest...
Self-attention is central to Transformer performance and is often the most expensive part of the Transformer at long context lengths because its pairwise token interactions scale q...
Policy-adherent tool-calling agents in customer-service domains must maintain task states across turns while calling tools and obeying domain policies. Task states consist of relev...
Attention-based Multiple Instance Learning aggregators in medical imaging are prone to attention concentration, producing overconfident and unstable predictions. We introduce QG-MI...
Robots operating in open-world environments must seamlessly integrate localization, spatial reasoning, navigation, and long-horizon planning. While specialist models excel at indiv...
Advances in radiance fields have enabled photorealistic novel view synthesis. In several domains, large-scale real-world datasets have been developed to support comprehensive bench...
This work presents a general framework for training large language models (LLMs) to "Connect the Dots" (CoD), a meta-capability required by long-lifecycle agents: as an LLM-based A...
World Action Models (WAMs) are embodied predictive-action models that make a forecast of the future available to action. Recent WAMs repurpose large video generation models, and a ...
The quadratic complexity of attention poses a critical bottleneck for long-context processing, spurring interest in hybrid attention designs. Most open-source hybrid models adopt a...
Reinforcement learning (RL) is a central approach for improving reasoning capabilities in large language models (LLMs), where training efficiency depends critically on how problems...
Achieving dexterous robotic manipulation in the real world heavily relies on human supervision and algorithm engineering, which becomes a central bottleneck in the pursuit of gener...
Video world models are moving toward preserving an observed world under controllable camera and object motion while allowing its environmental state to change. Yet these controls r...
Style-content dual-reference generation aims to synthesize an image that preserves the structure and semantics of a content reference while adopting the style of a separate style r...
Continual Test-Time Adaptation (CTTA) aims to maintain model performance under evolving target domains by adapting online without labeled data. However, practical deployments often...
World models are increasingly regarded as a decisive step toward artificial general intelligence, yet modeling the physical world demands more than rendering convincing frames on d...
Current AI-driven game development has made substantial progress in asset generation, gameplay design, and web-based game coding, yet project-level code engineering on professional...
MLLM-based mobile GUI agents have made substantial progress on short-horizon tasks, yet remain unreliable on long-horizon tasks that require retaining intermediate facts across man...
MLLM-based mobile GUI agents have made substantial progress in UI understanding and action execution, but adapting them to real target apps remains costly because mobile apps are n...
Omni-modal models can ingest video, audio, and text, but unified access to multiple modalities does not guarantee that a model uses the right evidence. This gap is especially prono...
Real-world spatial intelligence requires reasoning over a continuous and evolving 3D world, yet existing VLMs and tool-augmented agents largely remain tied to static, stateless inf...
Creating 3D visual illusions, a single 3D mesh that reveals entirely different semantics from various viewing angles, is a fascinating but tough challenge. Existing optimization-ba...
FP4 training promises substantial reductions in memory and computation cost for LLM pretraining, yet current FP4 hardware paths and recipes, including NVIDIA Blackwell/Rubin-class ...
LiveCodeBench (LCB) has recently become a widely adopted benchmark for evaluating large language models (LLMs) on code-generation tasks. By curating competitive programming problem...