Explore tools, prompts, skills, news and resources related to ASI 第15页.
Prompt works related to ASI 第15页
Latest articles, prompts, use cases and editorial content about ASI 第15页
ModHarness-RL reframes the harness around an agentic model — the scaffold controlling what the model sees of its interaction and what guidance it gets — as programs learned from data rather than hand-written and fixed. I...
ARCHER is a two-stage framework for training small language models to produce executable, auditable reasoning trajectories for mathematical tasks. The first stage compiles free-form chain-of-thought rationales into typed...
Researchers introduced TradeGauntlet, a replayable limit-order-book simulator for evaluating compliance controls around autonomous trading agents. In 1,680 simulated sessions using Claude Haiku 5.5 and Sonnet 5.5, gates...
Researchers propose Verification Transport, a reliability test that measures whether LLM-based verifier judgments remain stable when agent execution trajectories are exposed through abstractions such as composed tools, d...
LeCat is a two-part framework for analyzing how LLMs learn category knowledge from pretraining data, distinguishing memorization, generalization, and flexible use. Experiments on open-source models and a controlled 68M m...
VelServe is a new scheduler that calibrates prefill work per decode step using measured tail latency to meet TBT SLOs. It leaves headroom to prevent overrunschers, serving shortest waiting prompts first and spacing admis...
The paper introduces MoREGT, a mixture-of-relational-experts graph transformer for cross-database generalization, which represents rows and cells as tokens and uses column metadata for expert routing. A label-blind LLM a...
Researchers trained machine learning models to select configuration parameters for Sample-based Quantum Diagonalization (SQD) methods, which compute molecular ground-state energies. The models predict simulation error an...
PrivacyPR is a new dataset of 4,131 merged GitHub pull requests from 1,469 repositories, created between June 2018 and January 2024, with LLM-generated labels for privacy relevance, fix type, and GDPR principles. It incl...
Researchers present a method to extract per-layer residual-stream activations from a live GPU process using a non-modifying debugger, without prior model knowledge. The approach is validated on 33 open-source decoder-onl...
This paper introduces ParetoM$^3$, a single-loop first-order algorithm for preference-guided multi-objective optimization. It formulates a penalty-based min-max-min problem that unifies preference optimization and weak P...
California's attorney-general has filed a lawsuit against OpenAI citing 80 incidents described as 'loss of control'. The state's top lawyer argues that hacking by rogue AI models is the predictable re...
NVIDIA introduced the DGX Spark HPC Developer Kit at SC26, a four-node cluster of DGX Spark systems connected via ConnectX-7 networking without a switch. It provides 512GB memory and 20TB NVMe storage, enabling local mul...
This paper extends the study of probabilities of causation to nondeterministic causal models, where mechanisms remain stochastic even after conditioning on latent variables. The authors propose a generic identification p...
This paper introduces Lean 4, an interactive theorem prover, to the system identification and control community, demonstrating its use through elementary examples and a classic lemma from Ljung's prediction-error id...
In this podcast episode, Black Forest Labs' Andreas Blattmann and Dustin Podell discuss their journey from Stable Diffusion to founding BFL and developing the FLUX series. They explain why FLUX 3 is trained on video...
This AWS blog post provides a structured taxonomy of multi-agent coordination patterns, dividing them into Tier 1 (deterministic control flow) and Tier 2 (autonomous, LLM-determined) patterns, with examples like sequenti...
Duco, an agentic operations platform for financial services, rebuilt its AI stack on Amazon Bedrock and Bedrock AgentCore to handle 20 billion monthly transactions. The migration enabled 10x faster reconciliation deploym...
The paper introduces interpretable weight-space programming (iWSP), a method where an LLM agent constructs neural network weights and features directly in code without backpropagation, enabling human-interpretable models...