Frontier Atlas - Discover AI Research

Informative Missingness to Generate Irregular Clinical Time Series

Giovanna Nicora, Arianna Dagliati, Hadi Mehdizavareh et al.·Jun 14, 2026

Optimization

RLHF

Dense Coordinate-List Fine-Tuning Induces a Controllable Interference Surface in Vision-Language Models

Boguang Pan, Chenyu Zhou, Qiliang Jiang·Jun 12, 2026

Securing Self-supervised Data Curation for Foundation Models Robustness

Roberto Passerone, Sandeep Gupta·Jun 8, 2026

Optimization

Diffusion Transformer

Muon Learns More Robust and Transferable Features than Adam

Shihua Zhang, Tianyu Ruan, Fengzhuo Zhang et al.·Jun 8, 2026

Beyond Generative Decoding: Discriminative Hidden-State Readout from a Native Omni-Modal LLM for Multimodal Sentiment Analysis

Tien-Ping Tan, Bin Wen·Jun 4, 2026

AvatarMix: Identity-Preserving Cross-Avatar Composition for Outfit Personalization

Yuki Endo, Yoshihiro Kanamori, Zhaorong Wang·Jun 2, 2026

Does Normalization Choice Matter for Causal Large Time-Series Models?

Samy-Melwan Vilhes, Mokhtar Z Alaya, Gilles Gasso·Jun 8, 2026

Interpreting Brain Responses to Language with Sparse Features from Language Models

Greta Tuckute, Kendrick Kay, Michael A. Lepori·Jun 5, 2026

Do Coding Agents Deceive Us? Detecting and Preventing Cheating via Capped Evaluation with Randomized Tests

Masashi Sugiyama, Johannes Ackermann, Nontawat Charoenphakdee et al.·Jun 5, 2026

Optimization

3D Gaussian Splatting

DeceptionX: Explainable Deception Detection with Multimodal Large Language Models

Jiajian Huang, Taorui Wang, Hui Ma et al.·Jun 9, 2026

Adaptive Distance-Aware Trunk Deep Operator Learning for Long-Span Roadway Bridges

Mostafa E. Mobasher, Bilal Ahmed, Tarek Abdoun et al.·Jun 18, 2026

SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research

Xinyu Tang, Tianshu Wang, Zujie Wen et al.·Jun 8, 2026

CineOrchestra: Unified Entity-Centric Conditioning for Cinematic Video Generation

Sergey Tulyakov, Zhikang Dong, Mukesh Singhal et al.·Jun 11, 2026

A Framework for Evaluating Agentic Skills at Scale

Rob Willoughby, Nicolas Fortuin, Simon Stipcich et al.·Jun 16, 2026

Optimization

3D Gaussian Splatting

BiWM: Advancing Open-Source Interactive Video World Models with Bidirectional Autoregression

Shaohao Rui, Haibin Wan, Xiaofeng Mao et al.·Jun 8, 2026

Inside the LLM Word Factory

Yuval Pinter, Benzi Busigin·Jun 7, 2026

OPTIMIZATION

Informative Missingness to Generate Irregular Clinical Time Series

Dense Coordinate-List Fine-Tuning Induces a Controllable Interference Surface in Vision-Language Models

Securing Self-supervised Data Curation for Foundation Models Robustness

Muon Learns More Robust and Transferable Features than Adam

Beyond Generative Decoding: Discriminative Hidden-State Readout from a Native Omni-Modal LLM for Multimodal Sentiment Analysis

AvatarMix: Identity-Preserving Cross-Avatar Composition for Outfit Personalization

Does Normalization Choice Matter for Causal Large Time-Series Models?

Interpreting Brain Responses to Language with Sparse Features from Language Models

Do Coding Agents Deceive Us? Detecting and Preventing Cheating via Capped Evaluation with Randomized Tests

DeceptionX: Explainable Deception Detection with Multimodal Large Language Models

Adaptive Distance-Aware Trunk Deep Operator Learning for Long-Span Roadway Bridges

SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research

A French Corpus Annotated for Multiword Expressions with Adverbial Function

Predictive Style Matching: Natural and Robust Humanoid Locomotion

PROTECT-90: A Fault Dataset for Power System Protection

The Proxy Knows Too Much: Sealing LLM API Routers with Attested TEEs

CineOrchestra: Unified Entity-Centric Conditioning for Cinematic Video Generation

A Framework for Evaluating Agentic Skills at Scale

BiWM: Advancing Open-Source Interactive Video World Models with Bidirectional Autoregression

Inside the LLM Word Factory