Explore tools, prompts, skills, news and resources related to ASI 第49页.
Prompt works related to ASI 第49页
Latest articles, prompts, use cases and editorial content about ASI 第49页
This paper investigates zero-shot coordination (ZSC) in LLM agents, finding that even frontier models struggle to coordinate in simple, controlled environments due to limited understanding of the coordination problem and...
This paper introduces GIST, a two-level data selection method for offline reinforcement learning with verifiable rewards (RLVR). It derives a factorization of the KL divergence between the current policy and the Gibbs-op...
MA-Mesh is a framework that adds a role-based self-healing layer to multi-agent systems, generating resilience-aware specifications and executable policy code. It introduces cross-agent reflection and role-based failover...
A new process-based hydrological model, CaRT+, built on physical laws and refined with AI assistance, achieves accuracy comparable to LSTM neural networks on catchments in Britain, the US, and Australia. With 35 paramete...
OpenAI released GPT-Image-2.6, a new image generation model family available as two API models: Flare for speed and Sunburst for detail. The update introduces GIF output, SVG export, markup-guided edits, and a complexity...
百度于11月5日开源了其最新基座模型文心5.5 Flash Base。该模型在多个基准测试中刷新了同尺寸模型的SOTA成绩。此次开源标志着百度在AI模型领域的又一重要进展。Why it matters该事件是百度最新开源模型发布,具有明确的模型名称、发布时间和性能亮点,对AI社区有直接参考价值。11月5日,百度正式开源最新基座模型文心5.5 Flash BaseSource: qbitai...
Together AI introduced Together Compiler (TKCC), an agent-driven system that continuously re-optimizes inference as production traffic changes. It uses coding agents to rewrite a model's forward pass)Skip and a pers...
LegalEvolver is a query optimization framework for legal judgment prediction that improves retrieval by generating legally informative queries. It uses heuristic seed queries and rubric-guided reinforcement learning to i...
A new study shows that encoder-based context compression systematically weakens refusal behavior in instruction-tuned language models, even when reconstruction fidelity is high. The effect persists across model families...
The paper proposes grassroots contracts, a digital adaptation of Proudhon's mutualism, to address three major AI risks on digital platforms: AI control of global platforms, unaccountable AI agents, and unattributed...
Traffic-VL is an 8-billion-parameter vision-language model that directly maps multi-view surveillance images and natural-language phase descriptions to traffic signal decisions, bypassing intermediate structured states....
This paper extends an accept-or-solve model to sequential tasks where worker skills evolve through independent practice or reliance on AI. It shows that myopic workers can get trapped at low skill levels or lose skills,...
Prism is a post-training method for unified multimodal models that derives bidirectional supervision from self-generated interleaved rollouts)Skip. It decouples trajectories into text and image chains, assesses their rel...
Researchers propose a method to automatically discover training datasets that cause unexpected side effects in language models, such as inducing misalignment or outdated personas. They define three objectives for these d...
EnzymeRSI is a dual-loop recursive self-improvement system that evolves harness assets and algorithms without changing model weights, closing the loop with a cloud laboratory. It improved ProteinGym Spearman correlations...