MuSViT: A Foundation Vision Model for Sheet Music Representation
Foundation models have transformed vision and language processing by providing rich, reusable representations that transfer across diverse tasks. Sheet music, as a visual encoding ...
Papers
AutoTrainess: Teaching Language Models to Improve Language Models Autonomously
Training language models (LMs) remains a highly human-intensive process, even as frontier language model agents become increasingly capable at software engineering and other long-h...
Seeing Is Not Sharing: Some Vision-Language Models Overestimate Common Ground in Asymmetric Dialogue
In collaborative dialogue, shared perception does not guarantee shared interpretation. Mutual understanding must be established through interaction. We investigate whether vision-l...
SpheRoPE: Zero-Shot Optimization-Free 360 Panorama Generation with Spherical RoPE
We present a zero-shot, training-free and optimization-free framework for generating 360 panoramic images and videos by directly injecting spherical priors into pre-trained diffusi...
SeKV: Resolution-Adaptive KV Cache with Hierarchical Semantic Memory for Long-Context LLM Inference
Large language models increasingly operate over long contexts, where the KV cache becomes a dominant memory bottleneck: its size grows linearly with sequence length and must be ret...
3D HAMSTER: Bridging Planning and Control in Hierarchical Vision Language Action Models through 3D Trajectory Guidance
Hierarchical Vision-Language-Action (VLA) models decouple high-level planning from low-level control to improve generalization in robot manipulation. Recent work in this paradigm u...
Goku: A Million-Scale Universal Dataset and Benchmark for Instruction-Based Video Editing
Existing instruction-based video editing datasets commonly focus on single-task appearance editing, failing to meet the complex creative demands of real-world scenarios. To bridge ...
When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors
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...
GEAR: Guided End-to-End AutoRegression for Image Synthesis
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...
PhotoQuilt: Training-Free Arbitrary-Resolution Photomosaics via Bootstrapped Tiled Denoising
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...
SciIR: A Large-scale Training Dataset and Benchmark for Scientific Image Reasoning Generation
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...
Beyond Drug Discovery: The Nanotechnology Molecular Optimization (NMO) Benchmark
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...
LUMOS: A Semantic Operating-System Layer for Accessibility-Grounded AI Agents
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...
Monte Carlo Energy Aggregation for Mobile 3D Gaussian Splatting
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...
Nemotron-Labs-Diffusion-Image: Advancing Masked Discrete Diffusion for High-Resolution Image Synthesis
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...
TACO: Tool-Augmented Credit Optimization for Agentic Tool Use
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...
Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent
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 ...
GUICrafter: Weakly-Supervised GUI Agent Leveraging Massive Unannotated Screenshots
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...
Illuminating Unified Multimodal Model for Free-form Interleaved Text-Image Generation
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 ...
MuseBench: Benchmarking Intent-Level Audiovisual Arts Understanding in MLLMs
Audiovisual arts encompass diverse creative disciplines, including cinema, visual arts, stage performance, and game design, where artistic meaning arises from deliberate combinatio...
JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applications
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, ...
Beyond IID: How General Are Tabular Foundation Models, Really?
Foundation models for predictive machine learning on tabular data have recently gained significant traction in academia and industry. Research communities across disciplines are in...
SWE-INTERACT: Reimagining SWE Benchmarks as User-Driven Long-Horizon Coding Sessions
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...
Morphing into Hybrid Attention Models
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...