27Understanding Usage and Engagement in AI-Powered Scientific Research Tools: The Asta Interaction DatasetARXIV ArXiv RAG阅读文章 arrow_forward
27SOTAlign: Semi-Supervised Alignment of Unimodal Vision and Language Models via Optimal TransportARXIV ArXiv阅读文章 arrow_forward
27Show HN: Claude-File-Recovery, recover files from your ~/.claude sessionsHACKER_NEWS Hacker News阅读文章 arrow_forward
27Scale Can't Overcome Pragmatics: The Impact of Reporting Bias on Vision-Language ReasoningARXIV ArXiv阅读文章 arrow_forward
27Introducing the Stateful Runtime Environment for Agents in Amazon BedrockBLOGS_PODCASTS 博客与播客 AI Agent阅读文章 arrow_forward
27Bitwise Systolic Array Architecture for Runtime-Reconfigurable Multi-precision Quantized Multiplication on Hardware AcceleratorsARXIV ArXiv阅读文章 arrow_forward
27Implementing a Z80 / ZX Spectrum emulator with Claude CodeHACKER_NEWS Hacker News阅读文章 arrow_forward
27Building secure, scalable agent sandbox infrastructureHACKER_NEWS Hacker News AI Agent阅读文章 arrow_forward
27Show HN: Badge that shows how well your codebase fits in an LLM's context windowHACKER_NEWS Hacker News 大语言模型阅读文章 arrow_forward
27OpenAI's $110B funding round (investments from Amazon, Nvidia, SoftBank)HACKER_NEWS Hacker News阅读文章 arrow_forward
27Parakeet.cpp – Parakeet ASR inference in pure C++ with Metal GPU accelerationHACKER_NEWS Hacker News阅读文章 arrow_forward
27Google workers seek 'red lines' on military A.I., echoing AnthropicHACKER_NEWS Hacker News阅读文章 arrow_forward
27Spatio-Temporal Token Pruning for Efficient High-Resolution GUI AgentsARXIV ArXiv AI Agent阅读文章 arrow_forward
27Scaling Search Relevance: Augmenting App Store Ranking with LLM-Generated JudgmentsARXIV ArXiv 大语言模型阅读文章 arrow_forward
27Risk-Aware World Model Predictive Control for Generalizable End-to-End Autonomous DrivingARXIV ArXiv阅读文章 arrow_forward
27ReCoN-Ipsundrum: An Inspectable Recurrent Persistence Loop Agent with Affect-Coupled Control and Mechanism-Linked Consciousness Indicator AssaysARXIV ArXiv AI Agent阅读文章 arrow_forward
27MovieTeller: Tool-augmented Movie Synopsis with ID Consistent Progressive AbstractionARXIV ArXiv阅读文章 arrow_forward
27Discourse-Aware Dual-Track Streaming Response for Low-Latency Spoken Dialogue SystemsARXIV ArXiv 大语言模型阅读文章 arrow_forward
27AgentDropoutV2: Optimizing Information Flow in Multi-Agent Systems via Test-Time Rectify-or-Reject PruningARXIV ArXiv RAG阅读文章 arrow_forward
27Agency and Architectural Limits: Why Optimization-Based Systems Cannot Be Norm-ResponsiveARXIV ArXiv AI Agent阅读文章 arrow_forward