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 7, 2026

10 papers found

[object Object], [object Object], [object Object], [object Object] 11/5/2026 huggingface

computer vision

Open-vocabulary segmentation (OVS) enables models to segment a variety of concepts specified in natural language, removing the need for fixed label sets and fine-tuning. While recent OVS approaches have shown strong performance on natural images, they transfer poorly to Earth observation (EO) data d...

Keywords: open-vocabulary segmentation, Earth observation, satellite imagery, TerraMesh-Masks, TerraMind, geospatial AI, OpenStreetMap, Overture Maps

[object Object], [object Object], [object Object] 11/5/2026 huggingface

transformer architectures

Linear attention compresses context into a fixed-size key-value state for linear-time training and constant-memory inference. Gated delta-rule models decay this state and erase its prediction for an incoming key before writing a new value; Gated DeltaNet-2 (GDN-2) generalizes this with channel-wise ...

Keywords: linear attention, gated delta rule, matched-filter readout, sensitivity-allocated gating, constant-memory inference, length extrapolation

[object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 11/5/2026 huggingface

robotics

World-action models (WAMs) jointly model future traffic states and driving actions for end-to-end autonomous driving in intelligent transportation systems. However, their action learning remains dominated by expert-trajectory imitation, leaving unsafe alternatives close to expert trajectories insuff...

Keywords: autonomous driving, world-action models, safety, negative sampling, flow matching, end-to-end learning

[object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 11/5/2026 huggingface

natural language processing

Background: Cardiovascular care generates large volumes of clinical free-text documentation in local languages. However, clinical natural language processing (NLP) resources remain concentrated in English, and no existing benchmark is cardiology-specific, multilingual, and broad in entity coverage. ...

Keywords: clinical NLP, multilingual models, cardiology, named entity recognition, XLM-RoBERTa, CardioCCC, CardioLM, biomedical NLP

[object Object], [object Object], [object Object], [object Object] 11/5/2026 huggingface

transformer architectures

Mixture-of-Experts (MoE) models route each token to a few of many experts, yet what an individual expert is responsible for remains unsettled. Existing analyses count how often an expert is selected on domain-labeled corpora, an instrument that fixes the taxonomy in advance, stays coarse, and record...

Keywords: Mixture-of-Experts, Sparse AutoEncoders, Interpretability, LLM, Feature Attribution
View Paper

Yi Feng, Andrea Paudice 11/5/2026 arxiv

optimization

Adversarial Training (AT) is an important method for improving model robustness. We study the dynamics of deterministic Gradient Descent (GD) in AT. Most existing works in this direction focus on the small or vanishing step sizes regime, where GD resembles a continuous-time flow. However, such step ...

Keywords: adversarial training, gradient descent, large step sizes, implicit bias, optimization, sharpness, edge of stability, logistic regression

Qile Jiang, George Em Karniadakis 11/5/2026 arxiv

machine learning

LLM-guided evolutionary search uses AI agents to improve programs for mathematical and computational problems by iteratively refining solutions and combining high-scoring methods. However, the process is often slow because the LLM generates a long textual chain of thought for each round and must rep...

Keywords: LLM agents, evolutionary search, latent space reasoning, KV cache, program synthesis, scientific computing

Yixiao Wang, Peiyi Chen, Mustafa Mukadam, Shreekant Gayaka, Masayoshi Tomizuka, Son Tran 11/5/2026 arxiv

robotics

Learning dexterous manipulation from limited visual demonstrations is challenging because policies must acquire both perceptual grounding and precise control, while reinforcement learning (RL) in simulation can acquire rich control behaviors from large-scale interaction with privileged information. ...

Keywords: dexterous manipulation, reinforcement learning, flow matching, latent space, visual policy learning, bimanual manipulation, data efficiency, sim-to-real

Arpit Bahety, Skand Peri, Sriniket Ambatipudi, Chen Xu, Haruki Nishimura, Masha Itkina, Roberto Martín-Martín 11/5/2026 arxiv

robotics

Vision-Language-Action (VLA) models can perform a wide range of robotic manipulation tasks, but often fail during deployment. Teaching them to recover from these failures requires substantial corrective data: existing approaches learn to recover from failures by directly associating corrective actio...

Keywords: VLA, robotics, semantic interventions, abduction, correction learning, transfer learning, vision-language-action

Taiming Lu, Sachin Konan, Zhuang Liu 11/5/2026 arxiv

machine learning

AI-Scientists arrived, but a world for them to grow in did not. Human scientists take theirs for granted $-$ centuries of open problems and shared ideas, waiting in the scientific literature. To AI-Scientists, that world is readable but not runnable, so we build Scientist World for them: every resea...

Keywords: AI-scientists, automated_research, executable_environments, research_evaluation, scientific_automation, AI_for_science
Loading...

Preparing your export...