Browse and export your curated research paper collection
[object Object], [object Object], [object Object] 11/5/2026 huggingface
transformer architecturesLinear 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 ...
[object Object], [object Object], [object Object], [object Object] 11/5/2026 huggingface
computer visionOral cancer and the oral potentially malignant disorders (OPMD) that can precede it are visible on the oral mucosa, which makes smartphone photographs a promising tool for screening. Deep learning models for this task classify individual photographs. However, screening refers patients, not photograp...
[object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 11/5/2026 huggingface
natural language processingLLM pruning must preserve quality while meeting hardware- and workload-specific constraints on latency, throughput, and memory. Existing pruning workflows often target parameter counts, requiring practitioners to manually select model sizes that meet latency, throughput, and GPU memory limits. Howev...
[object Object], [object Object], [object Object], [object Object] 11/5/2026 huggingface
computer visionOpen-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...
[object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 11/5/2026 huggingface
roboticsWorld-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...
Yixiao Wang, Peiyi Chen, Mustafa Mukadam, Shreekant Gayaka, Masayoshi Tomizuka, Son Tran 11/5/2026 arxiv
roboticsLearning 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. ...
Qile Jiang, George Em Karniadakis 11/5/2026 arxiv
machine learningLLM-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...
Yi Feng, Andrea Paudice 11/5/2026 arxiv
machine learningAdversarial 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 ...
Yanlin Jin, Bowen Yang, Cheng Zhang, Yifan Yang, Zhe Li, Jianfei Cai, Kai Zhu 11/5/2026 arxiv
multimodal learningModern video models possess strong visual priors, yet do not natively represent human action in metric 3D space. We present EgoGeneralist, which adapts pretrained video generators to unify action-conditioned egocentric video generation, pose estimation, and joint action-video generation. Our role-ad...
Arpit Bahety, Skand Peri, Sriniket Ambatipudi, Chen Xu, Haruki Nishimura, Masha Itkina, Roberto Martín-Martín 11/5/2026 arxiv
roboticsVision-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...
Preparing your export...