Example Pairs Replace Prompts, Agents Play Favorites

Featured

• Spanning the Visual Analogy Space with a Weight Basis of LoRAs score 5
  机构: NVIDIA; 关键词(3): lightweight, inference, text-to-image
• GLM-5: from Vibe Coding to Agentic Engineering score 9
  入选 HF Daily Papers; HF 热度: 77 upvotes (+4); 关键词(8): efficiency, inference, alignment, post-training, agent
• Towards Efficient Constraint Handling in Neural Solvers for Routing Problems score 5
  关键词(4): efficient, efficiency, lightweight, search; 顶会接收: ICLR

Also Worth Noting

• Language Statistics and False Belief Reasoning: Evidence from 41 Open-Weight LMs score 4
  机构: MIT; 关键词(1): reasoning
• Examining Fast Radiative Feedbacks Using Machine-Learning Weather Emulators score 4
  机构: Allen Institute; 关键词(1): fast
• Automated Multi-Source Debugging and Natural Language Error Explanation for Dashboard Applications score 3
  机构: Oxford
• Bridging Day and Night: Target-Class Hallucination Suppression in Unpaired Image Translation score 3
  顶会接收: AAAI
• Transforming GenAI Policy to Prompting Instruction: An RCT of Scalable Prompting Interventions in a CS1 Course score 3
  机构: University of Toronto
• Enhancing Diversity and Feasibility: Joint Population Synthesis from Multi-source Data Using Generative Models score 2
  关键词(4): agent, planning, evaluation, synthetic data
• FrameRef: A Framing Dataset and Simulation Testbed for Modeling Bounded Rational Information Health score 2
  关键词(5): fine-tuning, agent, search, recommendation, evaluation
• When Remembering and Planning are Worth it: Navigating under Change score 2
  关键词(6): efficient, fast, agent, agents, planning
• Accelerating Large-Scale Dataset Distillation via Exploration-Exploitation Optimization score 2
  关键词(4): efficient, efficiency, distillation, deployment
• Visual Persuasion: What Influences Decisions of Vision-Language Models? score 6
  入选 HF Daily Papers; HF 热度: 3 upvotes (+1); 关键词(6): efficient, preference, agent, agents, vision-language
• High-Fidelity Network Management for Federated AI-as-a-Service: Cross-Domain Orchestration score 2
  关键词(3): inference, latency, guardrails
• Complex-Valued Unitary Representations as Classification Heads for Improved Uncertainty Quantification in Deep Neural Networks score 2
  关键词(4): scaling, lightweight, benchmark, safety
• Consistency-Preserving Diverse Video Generation score 2
  关键词(2): lightweight, text-to-video
• EAA: Automating materials characterization with vision language model agents score 2
  关键词(8): efficiency, agent, agents, agentic, reasoning
• Hybrid Federated and Split Learning for Privacy Preserving Clinical Prediction and Treatment Optimization score 2
  关键词(4): lightweight, deployment, inference, cost