Portada · pág. 48

← primera página

First-Order In-Context Shapley: Scalable Data Auditing for LLM Alignment and Evaluation
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
What Current AI Benchmarks Leave Unmeasured: Modality, Search, Citations, and Implications (for Safety Evaluations)
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
STAIR: Effective Incident Response Using an End-to-End Agentic Planning Framework
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
DASC: Decay-Aware State Compression for Hybrid Linear-Attention Serving
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Defense-as-Skill: Evolving Runtime Guard Skill for Skill-Augmented Agents
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Protocol effects on feature-based hardware-Trojan detection across Trust-Hub families
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
TDDN: Text-aligned Diffused DINO Network for Puzzle Understanding
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
SUN: Reaching for Novelty in Reinforcement Learning
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
What Makes Adversarial Examples Transfer Across Deepfake Detectors?
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Trust, but Validate the Instrument: Auditing AI-Generated RTL Verification Plans on Authored Security-Regression Proxies
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
RLVR$^{2}$: Reinforcement Learning with Verifiable Rubric-based Ranking
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
ThinkNet: Evolutionary Deep Ensembles for Efficient Motor-Imagery EEG Classification
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Graph World Models for Constrained Epidemic Policy Planning
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
MS-GLA: Multi-Scale Gated Linear Attention for Addressing Representational Bottlenecks via Multi-Temporal Resolution
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
FACT: Fidelity-Aware Construction of Articulated Twins
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
OpenCollab: A Multi-Agent Coding Framework with Programmable Collaboration and Controllable Runtime
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Making LLMs Say What They Think: Measuring and Improving CoT-Interpretability Alignment
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Scale and Selection: What Makes Automatic Harness Evolution Work for Visual-Interface Robot Agents
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Selection-Based Structured Reasoning: Toward Efficient Multimodal Search Agents
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
GOTT: Object-centric Dexterous Manipulation with a Reusable Cross-Embodiment Primitive
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Solving VeriContest with a Lean-Backed Rust Verifier
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
AgroGround: Multi-Granularity Grounded Recognition in Agriculture
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Video2World: Benchmarking Coding Agents for Interactive World Modeling from Embodied Videos
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Green-Routed Neural Operators: Physics Determines Where the Network Reads
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Work While They Sleep: Exploiting Evaluation Latency for Fully Bayesian Optimization
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
Decoupling Logic from Persona: Structural Immunity of Edge LLM Agents to Context Pollution
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
PHRBench: A Behavioral Evaluation of Post-Hallucination Reasoning in LLMs
arXiv cs.AIarxiv.orgAgregado: 12/10/2026, 18:00:45Publicado: 13/10/2026, 4:00:00detalle
A look at the math that OpenAI claims computes faster Fourier transforms
Hacker Newsargmin.netAgregado: 13/10/2026, 14:01:10Publicado: 13/10/2026, 2:46:43detalle
AI models can provably hide arbitrary capabilities
Hacker Newsarxiv.orgAgregado: 13/10/2026, 14:01:10Publicado: 13/10/2026, 2:07:08detalle
Por qué el pendrive es el peor lugar donde puedes guardar tu copia de seguridad
WWWhat's newwwwhatsnew.comAgregado: 13/10/2026, 14:01:10Publicado: 13/10/2026, 2:00:08detalle
Vi Hart's Big Navier-Stokes Post
Lobste.rspatreon.comAgregado: 13/10/2026, 14:01:10Publicado: 13/10/2026, 1:29:49detalle
Open Thread 455
Astral Codex Tenastralcodexten.comAgregado: 13/10/2026, 14:01:10Publicado: 13/10/2026, 0:19:32detalle
Show HN: SolidCraft – Open-Source Parametric CAD in Rust (With MCP Support)
Hacker Newsgithub.comAgregado: 13/10/2026, 14:01:10Publicado: 13/10/2026, 0:11:04detalle
Japón lleva desde 2011 vendiendo más pañales para adultos que para bebés: lo que eso dice del mundo que viene
WWWhat's newwwwhatsnew.comAgregado: 13/10/2026, 14:01:10Publicado: 13/10/2026, 0:00:20detalle
Meta Wonder 🤖, X's resurgence 📈, why WebMCP matters 🌍
TLDR Techtldr.techAgregado: 13/10/2026, 14:01:10Publicado: 13/10/2026, 0:00:00detalle
Bitcoin Optech Newsletter #426 Recap Podcast
Bitcoin Optechbitcoinops.orgAgregado: 14/10/2026, 14:01:36Publicado: 13/10/2026, 0:00:00detalle
The Origin Story of Kid Pix
Hacker Newsred-green-blue.comAgregado: 14/10/2026, 14:01:36Publicado: 12/10/2026, 23:52:29detalle
Maytham Alsudany: Menus without JavaScript
Planet Debianmaytham.aezign.auAgregado: 13/10/2026, 14:01:10Publicado: 12/10/2026, 23:34:00detalle
Can GLP-1s Slow Aging?
Nautilusnautil.usAgregado: 13/10/2026, 14:01:10Publicado: 12/10/2026, 23:00:00detalle
Janas: Run LLMs larger than RAM by streaming experts from SSD
Hacker Newsgithub.comAgregado: 13/10/2026, 14:01:10Publicado: 12/10/2026, 22:05:43detalle
El dron que el ejército de EE.UU. desplegó sin baterías ni señal de radio: PowerLight ARC en la base Shaw
WWWhat's newwwwhatsnew.comAgregado: 13/10/2026, 14:01:10Publicado: 12/10/2026, 22:00:23detalle
Mere Minutes With AI Causes a Sharp Drop in Persistence
Nautilusnautil.usAgregado: 13/10/2026, 14:01:10Publicado: 12/10/2026, 22:00:00detalle
LumineCapture Is a New Screenshot Tool Built for Speed on Linux
Linuxiaclinuxiac.comAgregado: 13/10/2026, 14:01:10Publicado: 12/10/2026, 21:43:36detalle
AI is a tool and using it well takes skill
Hacker Newsyyhh.orgAgregado: 13/10/2026, 14:01:10Publicado: 12/10/2026, 21:40:18detalle
Intel D270 GPU AI Accelerator–Up to 480 GB LPDDR5X
Hacker Newsintel.comAgregado: 13/10/2026, 14:01:10Publicado: 12/10/2026, 21:35:35detalle
Steinar H. Gunderson: Decompilation patterns part 9, sign extension
Planet Debianblog.sesse.netAgregado: 13/10/2026, 14:01:10Publicado: 12/10/2026, 21:12:00detalle
Kcgi – minimal CGI and FastCGI library for C/C++
Hacker Newskristaps.bsd.lvAgregado: 14/10/2026, 14:01:36Publicado: 12/10/2026, 21:09:08detalle
PS5 Pro sin stock hasta 2027 y GTA 6 en noviembre: la tormenta perfecta que va a vaciar las estanterías
WWWhat's newwwwhatsnew.comAgregado: 13/10/2026, 14:01:10Publicado: 12/10/2026, 20:00:21detalle
Writing a Demoscene Intro for the ZX Spectrum
Hacker Newsmarkround.comAgregado: 12/10/2026, 18:00:45Publicado: 12/10/2026, 19:40:00detalle
Making big downloads resumable in Firefox
Hacker Newslunarwatcher.codeberg.pageAgregado: 13/10/2026, 14:01:10Publicado: 12/10/2026, 19:36:02detalle