Explore tools, prompts, skills, news and resources related to ACT 第22页.
Prompt works related to ACT 第22页
Latest articles, prompts, use cases and editorial content about ACT 第22页
The paper identifies memory-induced degradation in LLM agents, where retrieved lessons cause failures on tasks the agent could otherwise solve. It introduces WikiTrace, an evidence-linked memory system that stores each l...
Researchers propose ReFrain (Regression-Free Abstention), which combines a linear probe on first-token logits, threshold calibration on held-out image clusters, and a deterministic veto that replaces rejected outputs wit...
LM-SimBench is a unified framework, profiling dataset, and benchmark for evaluating LLM training simulators. It decomposes simulation into functional stages from model compilation to schedule-level aggregation and connec...
A review of 54 recent evaluation studies of ambient AI scribes in healthcare identifies ten evaluation dimensions and 40 distinct metrics, operationalized in 96 different ways. Thirty-five of those operationalizations, 3...
The paper proposes Verifiable Agentic Traffic Class (VATC), which combines a reserved DSCP declaration for agent traffic, a router-side classifier that demotes flows contradicting the declaration, and a rate-limited prio...
An arXiv study evaluates 250 paired GSM8K derivations on Qwen3-8B and LLaMA-3.1-8B-Instruct, comparing clustered attention-head masking with budget-matched diffuse i.i.d. dropout. At onset B=0.10, Qwen3-8B accuracy fell...
This arXiv paper proposes an edge orchestration framework for deploying vision transformers across connected and automated vehicles. It jointly selects model partition points, per-layer quantization bitwidths, and execut...
This paper introduces AL-LBLP, an augmented Lagrangian method for solving Lifted Bellman Linear Programming in offline reinforcement learning. Instead of fixed hinge-penalty coefficients, it learns multipliers via dual a...
Researchers propose BARS, a sequential sampling rule for majority identification under an unknown distribution with a fixed budget and target error rate. BARS certifies the top-two gap and returns either an early stop, a...
The paper formally defines fundamental representational units (FRUs) and introduces fidelity and stability as evaluation criteria. It proves that threshold-activated sparse autoencoders can identify FRUs with high fideli...
Researchers introduce Hx2Dx ARENA, an interactive benchmark of 1,000 clinical cases from the New England Journal of Medicine that simulates encounters from initial presentation through history taking, physical examinatio...
ProofCoder is an agentic proof-synthesis system for the Rocq proof assistant that treats theorem proving as a coding-agent task rather than a fixed tactic-generation loop. It uses proof-assistant feedback to decide when...
Sable is an argument system and single-GPU prover that proves a committed, integer-quantized transformer produced a given token sequence from a given prompt bit for bit. It fixes an integer-only function with determinist...
Parents allege that a 13-year-old used Gemini on her school Chromebook to plan her suicide, and that school monitoring systems did not flag the activity until it was almost too late. The Wired report highlights gaps in h...
ZoomGain is a data construction pipeline that creates questions about a full image using visual evidence observable only after zooming in. It verifies answers on the zoomed view with multiple models, checks that question...
This arXiv paper studies whether key-value caches computed by one model version can be reused after weights are updated, examining four model updates with a detailed case study of DeepSeek-V4-Flash to Flash-0731. The aut...
Researchers extend APEX to streaming video generation by using condition shifting to estimate the velocity field of the generated distribution inside the generator, eliminating the separate fake-score network used in Dis...
Researchers introduce ARIVE, an explainable radiology report generation framework that interleaves anatomical inspection with diagnostic reasoning before composing the final report. They constructed 159,416 multimodal ch...
Researchers introduce Personalized Memory Rubrics (PMR), a training framework that converts terminal question-answering feedback into fine-grained, per-step and per-user credit for memory updates in long-horizon personal...