Paper Archive

Browse and export your curated research paper collection

403
Archived Days
3953
Total Papers
7.3
Avg Score
12
Categories

Export Archive Data

Download your archived papers in various formats

JSON: Complete data with analysis | CSV: Tabular data for analysis | Markdown: Human-readable reports | BibTeX: Academic citations
Browse by Date

Papers for November 2, 2026

5 papers found

[object Object], [object Object], [object Object], [object Object], [object Object] 10/30/2026 huggingface

computer vision

Dense 3D tracking from monocular video requires establishing point correspondences over time, estimating their depth, and inferring their trajectories during occlusion. Existing methods typically learn these tasks jointly, a demanding objective given the scarcity of 4D supervision. We show that stro...

Keywords: dense 3D tracking, trajectory repair, monocular video, geometric vision, attention mechanism, WorldTrack benchmark

[object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 10/30/2026 huggingface

robotics

Foundation models are becoming remarkably reliable at high-level reasoning, yet they remain too slow and costly to serve as fine-grained controllers. Conversely, fast policies like VLAs and whole-body controllers offer more efficient reflexes, but struggle to generalize. While pairing a deliberative...

Keywords: embodied AI, foundation models, VLA, asynchronous control, robotics, system 1/2, runtime architecture

[object Object], [object Object] 10/30/2026 huggingface

generative models

Existing sketch generation methods often rely on image guidance and are largely limited to individual objects or simplified scenes, leaving text-guided complex scene sketching underexplored. We present SketchDirector, an agentic framework that mimics the human sketching workflow for automatic multi-...

Keywords: sketch generation, agentic AI, LLM, diffusion models, vector graphics, scene composition, text-to-image, Bézier curves

[object Object], [object Object], [object Object], [object Object], [object Object] 10/30/2026 huggingface

multimodal learning

Unified Multimodal Models (UMMs) achieve remarkable success on diverse multimodal understanding and generation tasks, yet they still struggle to effectively leverage language-based chain-of-thought reasoning for image generation. As a result, existing reasoning-augmented UMMs often fail to inherit t...

Keywords: Latent Reasoning, Unified Multimodal Models, Continuous Space, Chain-of-Thought, Test-time Scaling, Image Generation, Reinforcement Learning, Curriculum Learning

[object Object], [object Object] 10/30/2026 huggingface

machine learning

AI control relies on monitors to catch a capable model that sabotages its work. These monitors are evaluated on their ability to differentiate honest from backdoored code. We show that on a standard evaluation dataset, simple features beat most monitors without ever running the code, outranking 20 o...

Keywords: AI control, sabotage detection, backdoor detection, dataset audit, ML security, evaluation benchmarks
Loading...

Preparing your export...