Latest AI/ML research from ArXiv and Papers with Code
While large language models (LLMs) perform well on table tasks, they still make data referencing errors (DREs), i.e., incorrectly citing or omitting table values, despite understan...
Visual generative models are typically trained in two stages. A tokenizer is first trained for reconstruction and then frozen, after which a generator is trained on its discrete in...
Photomosaics are large images whose local regions are seen as independent tiles while their overall arrangement forms a coherent scene. Generating them at high resolution, with eve...
While Text-to-Image (T2I) models have shown remarkable success in generating photorealistic visual content, they still struggle with the rigorous semantic alignment and logical rea...
Generative molecular design is shaped by simple proxy benchmarks for drug-like properties and models pretrained on large pharmaceutical datasets. This combination yields strong ben...
Current operating systems expose interfaces optimized for human users but not for AI agents. Humans benefit from pixels, icons, windows, visual grouping, mouse movement, and keyboa...
Recent advances in 3D Gaussian Splatting have demonstrated unprecedented success in novel view synthesis. However, the substantial inference and storage overhead driven by high-ord...
We propose Nemotron-Labs-Diffusion-Image, a state-of-the-art masked discrete diffusion model (MDM) for high-resolution text-to-image synthesis. Compared with prior work on masked i...
Agentic multimodal models perform diverse operations on an image via code and reason over the returned view, an effective paradigm for fine-grained visual question answering. Howev...
We introduce Agents-A1, a 35B Mixture-of-Experts Agentic Model that reaches trillion-parameter-level performance by scaling the agent horizon. We investigate agent-horizon scaling ...
Data, as the fundamental substrate of modern intelligence, has greatly driven the development of current foundation models. Naturally, researchers aim to extend this paradigm to th...
The advancement of generative AI models capable of producing text and image marks a critical step forward in the realm of multimodal intelligence, particularly for tasks involving ...
Audiovisual arts encompass diverse creative disciplines, including cinema, visual arts, stage performance, and game design, where artistic meaning arises from deliberate combinatio...
JD.com, one of the world's largest e-commerce platforms, serves over 700 million active users and millions of merchants, with a catalog of tens of billions of SKUs. At this scale, ...
Foundation models for predictive machine learning on tabular data have recently gained significant traction in academia and industry. Research communities across disciplines are in...
We introduce SWE-Interact, a new testbed for evaluating coding agents on multi-turn, interactive, user-driven software engineering tasks. Existing frontier SWE benchmarks typically...
Hybrid attention models improve long-context efficiency by retaining only a subset of full-attention layers and replacing the remaining layers with linear attention. However, the e...
While large language models have been dominating the research landscape recently, small language models remain highly relevant across various domains; yet, they receive far less at...
Audio-video generation has recently gained unprecedented research attention, aiming to synthesize high-quality sounding video content with fine-grained synchronization and semantic...
On-policy distillation (OPD) offers superior capacity transfer by supervising student-sampled trajectories with dense token-level signals. To furnish high-quality supervision sourc...
We present DreamForge-World 0.1 Preview, a preview foundational world model for real-time interactive world simulation. The system adapts the LongLive 1 autoregressive video stack,...
Interactive video generation systems for camera-controlled world exploration roll out growing sequences of latent video frames, entangling state transition with high-frequency obse...
In real-world applications, guardrails are often expected to identify unsafe user-model interactions according to application-specific safety policies, rather than relying on prede...
MLLM-based GUI grounding methods commonly formulate target localization as autoregressive coordinate generation, enabling models to leverage the strong instruction-following and se...