OpenLongTail: Generative Scaling of Long-Tail Driving Data
Scaling robust driving policies is fundamentally bottlenecked by the scarcity of edge cases in curated datasets. While the real world continuously captures these critical events, s...
Papers
Self-Guided Test-Time Training for Long-Context LLMs
Long-context processing has become increasingly important for large language models (LLMs), but simply extending the context window does not guarantee effective utilization of long...
Video Generation Models are General-Purpose Vision Learners
Driven by next-token prediction, NLP shifted from task-specific models into powerful generalist foundation models. What, then, is the equivalent catalyst needed to achieve a genera...
A Sovereign, Open-Source Foundation Model for German and English
We present Soofi S 30B-A3B, a sovereign, open-source Mixture-of-Experts (MoE) hybrid Mamba Transformer foundation model for German and English. Its hybrid design activates only 3B ...
Scalable Visual Pretraining for Language Intelligence
The rapid progress of large foundation models has been driven predominantly by pretraining on large-scale text corpora. However, many forms of knowledge are conveyed through visual...
On Locality and Length Generalization in Visual Reasoning
A striking feature of the human visual system is that it ingests visual information through a series of local foveated glimpses, rather than a single global computation. This makes...
Phone Segmentation and Recognition through Phonological Activation Mapping
Phone segmentation and recognition are inherently related tasks, yet modern approaches typically model them separately. We argue that phonetic structure is already latent in the re...
PanoWorld: Real-World Panoramic Generation
In this work, we aim to address the challenge of long-range memory in panoramic world models by exploiting the rotation-equivariant property of omnidirectional representations, whe...
Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning
Fine-tuning LLMs to inject new knowledge faces a critical challenge: LLMs can quickly memorize new facts, yet fail to use them for downstream reasoning tasks. We formalize this fai...
ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation
Generating realistic 3D human motions in real-time within interactive applications is key for animation, simulation, and humanoid robotics. While recent offline motion generation a...
LongE2V: Long-Horizon Event-based Video Reconstruction, Prediction, and Frame Interpolation with Video Diffusion Models
Recovering high-quality video from sparse event streams is a challenging task. Regression methods often blur textures, while existing generative models struggle with long-term stab...
Enhancing In-context Panoramic Generation via Geometric-aware Pretraining
In this work, we present Canvas360, a two-stage framework for in-context panoramic generation that combines geometry-aware pretraining with downstream task-specific fine-tuning. To...
A Quantized Native Runtime for On-Device Semantic Audio Generation
Semantic audio applications increasingly require controllable generation on commodity and embedded hardware rather than through framework-heavy datacenter stacks. We present aria, ...
What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness
Large language models fine-tuned for forecasting can be accurate yet poorly calibrated, and their chain-of-thought (CoT) reasoning may not faithfully reflect the evidence behind a ...
UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks
The rapid development of large language models and multimodal large language models has accelerated the emergence of proactive agents capable of operating everyday tools and assist...
CausalDS: Benchmarking Causal Reasoning in Data-Science Agents
Large language models (LLMs) increasingly act as integrated data-science agents, combining abstract reasoning with advanced tool use. Yet the relevant benchmark landscape largely d...
Blind-Spots-Bench: Evaluating Blind Spots in Multimodal Models
Modern AI models achieve strong performance on many established benchmarks, yet they still fail on tasks that humans find almost trivial, such as manipulating a string or drawing a...
Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation
Visual generators excel at rendering, but they confidently fabricate what they do not know. User requests are unbounded, evolving, and deeply long-tailed: new characters, trending ...
Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation
Scientific ideas rarely start from a blank page. They inherit mechanisms, repair known limitations, and recombine pieces of earlier work, much like biological genomes. Current benc...
OpenCoF: Learning to Reason Through Video Generation
Reasoning has become a core capability for large models, especially when reliable decisions require understanding logical consequences. Recent video generation models offer a reaso...
OPSD-V: On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators
We propose OPSD-V, an on-policy self-distillation paradigm for post-training few-step autoregressive (AR) video diffusion models. Existing few-step AR video generators can produce ...
MuScriptor: An Open Model for Multi-Instrument Music Transcription
Existing methods for automatic music transcription are often limited to single-instrument recordings or fail on complex, real music mixes. Although previous work utilizes synthetic...
DrugGen 2: A disease-aware language model for enhancing drug discovery
Current computational approaches for drug design typically focus on generating molecules conditioned on specific targets or general molecular properties, often neglecting the influ...
Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading
AI agents have become capable of autonomously completing short, well-specified tasks. However, existing terminal benchmarks largely focus on simple problems that finish within minu...