Research radar
arXiv preprints, filtered for developer impact.
Concise summaries of new AI papers, ranked for how likely they are to change how production systems are built. arXiv collection remains rate-limited.
Papers tracked
1,289
1 arXiv sources
Top radar
86
http://arxiv.org/abs/2607.13027v1
Published 24h
59
by paper date
Rate limit
1/3s
arXiv policy
| Paper | Authors | arXiv ID | Categories | Published | Code | Radar | Summary |
|---|---|---|---|---|---|---|---|
| LLM for EDA in Front-End Design: Challenges and Opportunities | Kangwei Xu, Bing Li, Ulf Schlichtmann | http://arxiv.org/abs/2607.09616v1 | cs.ET, cs.AR | Jul 10, 2026 | None | RDR63 | As chip complexity increases and time-to-market pressures grow, front-end design has become a... |
| Toward Real-Time Sentence-Level Sign Language Translation | Thanh-Hoang Nguyen Doan | http://arxiv.org/abs/2607.09611v1 | cs.CL | Jul 10, 2026 | None | RDR63 | Most sign language understanding systems operate at the level of isolated signs, limiting the... |
| TrustX Agent Risk Classification Framework (ARC): Risk-Tiering Internally Created Agentic AI Systems | Hannah M. Liu, Rhea Saxena, Shiv Asthana | http://arxiv.org/abs/2607.09586v1 | cs.AI | Jul 10, 2026 | None | RDR63 | The proliferation of agentic AI systems across enterprise and public-sector contexts has outp... |
| TCLA: Training-Free Class-wise Logit Adaptation for Medical Vision-Language Models | Tianyou Jiang, Ziyu Zhou | http://arxiv.org/abs/2607.09562v1 | cs.CV, cs.AI | Jul 10, 2026 | None | RDR73 | Medical Vision-Language Models (VLMs) exhibit strong zero-shot performance, yet their effecti... |
| OPSD-V: On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators | Hongyu Liu, Chun Wang, Feng Gao | http://arxiv.org/abs/2607.08766v1 | cs.CV | Jul 9, 2026 | None | RDR69 | We propose OPSD-V, an on-policy self-distillation paradigm for post-training few-step autoreg... |
| Dimensionality Reduction Meets Network Science: Sensemaking on UMAP's kNN Graph | Duen Horng Chau, Donghao Ren, Fred Hohman | http://arxiv.org/abs/2607.08746v1 | cs.LG, cs.AI | Jul 9, 2026 | None | RDR81 | While UMAP is widely used for exploring high-dimensional data, typical workflows focus on its... |
| Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents | Yifan Wu, Lizhu Zhang, Yuhang Zhou | http://arxiv.org/abs/2607.08716v1 | cs.AI, cs.CL | Jul 9, 2026 | None | RDR72 | In long-horizon tasks, decision-relevant state is often scattered across an expanding traject... |
| DepthWeave-KV: Token-Adaptive Cross-Layer Residual Factorization for Long-Context KV Cache Compression | Anna Cordoba, Adam Puente Tercero, Nerea Angulo Hijo | http://arxiv.org/abs/2607.06523v1 | cs.AI | Jul 7, 2026 | None | RDR85 | Long-context language model inference is increasingly limited by the memory bandwidth and cap... |
| Relaxing Faithfulness with Intervention-Only Causal Discovery | Bijan Mazaheri, Jiaqi Zhang, Caroline Uhler | http://arxiv.org/abs/2607.11816v1 | cs.LG, stat.ML | Jul 13, 2026 | None | RDR64 | Causal discovery algorithms learn a network that describes the causal dependencies among rand... |
| OpenLongTail: Generative Scaling of Long-Tail Driving Data | Lulin Liu, Nuo Chen, Yan Wang | http://arxiv.org/abs/2607.09655v1 | cs.CV | Jul 10, 2026 | None | RDR72 | Scaling robust driving policies is fundamentally bottlenecked by the scarcity of edge cases i... |