Paper page - Dynamic Latent Routing
…View arXiv page View PDF Add to collection Community Humans live in a continuous world, yet think in discrete language. LLMs live in a tokenized world, yet think in continuous representations. So…
Search
Paper page - APEX: Large-scale Multi-task Aesthetic-Informed Popularity Prediction for AI-Generated Music
…AI-generated summary Music popularity prediction has attracted growing research interest, with relevance to artists, platforms, and recommendation systems. However, the explosive rise of AI-generated music platforms has created an entirely…
Paper page - COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation
…a capability track for practices, mental models, and decision heuristics, and a bounded behavior track for communication style, interaction rules, and correction history. The package can be inspected, invoked, updated through natural…
Paper page - When Cloud Agents Meet Device Agents: Lessons from Hybrid Multi-Agent Systems
…View arXiv page View PDF Add to collection Community If you use an edge device-sized, or self hosted, LM to power your agentic system, you will usually observe subpar performance; on…
Paper page - LLM-based Detection of Manipulative Political Narratives
…View arXiv page View PDF GitHub 2 Add to collection Community We present a new computational framework for detecting and structuring manipulative political narratives. A task that became more important due to…
Paper page - Reducing Political Manipulation with Consistency Training
…Community X: https://x.com/longphan3110/status/2058933197535170787 This is an automated message from the Librarian Bot . I found the following papers similar to this paper. The following papers were recommended by…
Paper page - Chiaroscuro Attention: Spending Compute in the Dark
…View arXiv page View PDF Add to collection Community A few threads I'd love to explore with the community: Routing collapse as a design principle — the router rejected RBF entirely and…
Paper page - Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation
…16k Add to collection Community This is an automated message from the Librarian Bot . I found the following papers similar to this paper. The following papers were recommended by the Semantic Scholar…
Paper page - OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories
…We are excited to open-source the OpenSeeker-v2 model weights and share our simple yet effective findings to make frontier search agent research more accessible to the community. View arXiv page…
Paper page - AcademiClaw: When Students Set Challenges for AI Agents
…We hope that AcademiClaw and its open-sourced data and code can serve as a useful resource for the OpenClaw community, driving progress toward agents that are more capable and versatile across…