Strumień wydarzeń
Wszystko, co pojawiło się w monitorowanych źródłach – od najnowszych.
-
TeamGym: A Gym for Team Decision-Making by AI Agents with Distributed Information
[Sztuczna inteligencja] Autorzy: Chanwoo Park, Jaywoong Jeong, Zachary Wojtowicz i 4 więcej Many real-world decisions require teams to integrate information distributed across participants. Yet AI agents are still primarily trained and benchmarked in isolation. We introduce TeamGym, an environment for evaluating and training language model-based agents on team decision-making problems constructed from real-world legal, finance, medical, and software engineering corpora. TeamGym introduces a method to identify a minimal set of facts, each element of which is necessary and all of which are collectively sufficient for a correct final decision, which we call pivotal information. This enables TeamGym to both control the distribution of pivotal information and track how well agents identify and integrate pivotal information when making team decisions. Examining 8 language models on 12 source corpora, we find that current AI agents often fail to effectively share information: Distrib…
-
Gym-Anything-RT: Scaling Real-Time Environments for Vision-Language Agents
[Uczenie maszynowe] Autorzy: Pranjal Aggarwal, Sean Welleck AI agents have made substantial progress in domains where they have a non-trivial amount of time to deliberate between actions, such as mathematics, software engineering, and performing tasks on desktop applications. It is less clear how such models fare in settings that demand real-time interaction, such as playing a video game or operating a physical device. In these settings, the environment state may evolve as the agent is reasoning, or even as the underlying model is performing a forward pass. To gain insight into the real-time interaction capabilities of vision-language agents, we introduce Gym-Anything-RT. Our key idea is to construct visual minigames that demand a portfolio of capabilities required for interactive real-time settings. Gym-Anything-RT uses an agentic pipeline to automatically generate such environments based on a taxonomy of six capabilities required for real-time…
-
When uncertainty quantification fails: structural vulnerabilities and corrections for selective prediction under clinical class imbalance
[Uczenie maszynowe] Autorzy: Walter Endrizzi, Flavio Ragni, Raffaele Marchesi i 4 więcej Background. Selective prediction systems improve the safety of clinical artificial intelligence by deferring ambiguous cases to human experts while automating high-confidence decisions. However, this safety mechanism relies entirely on the premise that uncertainty scores accurately reflect clinical ambiguity. In prognostic tasks characterized by severe class imbalance, where the clinical outcome of interest is a minority, this assumption breaks down. Standard uncertainty measures cease to capture clinically aligned ambiguity; instead, they become a proxy for class membership, systematically penalizing minority patients regardless of their individual predictive clarity. Results. Across 56 synthetic conditions and three neurodegenerative cohorts spanning severe class imbalance to near-balanced conditions (multiple sclerosis, Parkinson's Disease, Alzheimer's Disease), our framework consist…
-
Introducing LFM3: Every Modality for Specialized Intelligence
164 punktów · 62 komentarze · autor Philpax · www.liquid.ai
-
Kinematic Constraint-Referenced Evaluation for Articulated Object Manipulation
[Robotyka] Autorzy: Baptiste Bonin, Caro Strickland, Audrey Durand Manipulation policies are evaluated predominantly by binary task success, which cannot tell whether the commanded gesture is the one the object's kinematics admit. We introduce Constraint-Referenced Strategy (CRS), which projects the commanded end-effector twist onto the object's joint axis, separating progress along the joint from off-constraint waste. CRS requires a joint model and a joint-following scripted controller derived from it, but no recorded demonstration or learned judge. On 74 simulated articulated objects, success registers three transfer failures as lower rates but attributes none, while the two CRS channels give each a distinct signature. A door-trained behavior-cloning policy opens drawers in 59 of 110 episodes, and in these passes it commands about $40\times$ the off-axis rotation of a drawer-trained policy's passes ($1.27$ vs.\ $0.032$~rad/s). Relative to a scripted …
-
When, Where, and What to Correct: Human-Guided Adaptive Residual Correction for Robot Policies
[Robotyka] Autorzy: Anukriti Singh, Maxime Caniot, Pratap Tokekar i 1 więcej Imitation policies that reliably execute most of a manipulation trajectory can still fail in localized regions requiring last-mile precision. Updating the full policy or exploring residual actions everywhere treats this local failure as a global learning problem. We introduce Adaptive Residual Correction (ARC), a lightweight post-training module that uses reinforcement learning (RL) to learn a residual correction on top of a frozen policy while using sparse human corrections to structure autonomous exploration. Rather than treating human corrections as imitation targets, ARC uses pre-intervention states to determine 'when' residual control should become active and correction geometry to determine 'where' in residual action space autonomous refinement should explore; task reward determines 'what' residual is ultimately executed. Across three precision-manipulation tasks on a real robot, …
-
GroundControl: Satellite-Conditioned Multi-View Diffusion for Reconstruction-Free Novel View Synthesis
[Widzenie komputerowe] Autorzy: Akshay Krishnan, Matias Turkulainen, Jamie Wynn i 7 więcej Multi-view or video diffusion models have recently emerged as state-of-the-art approaches for novel-view synthesis from sparse image collections. While they can produce high quality images, they tend to hallucinate unrealistic spatial layouts when synthesizing views outside the input views (scene extrapolation). We propose to address this challenge for outdoor scenes by using satellite images as an additional information source to condition the multi-view generative model. We introduce a new satellite-conditioned multi-view diffusion model that combines conditioning from a satellite image and street-level input images when generating novel-views. Our cross-attention based conditioning allows us to retain pretrained multi-view diffusion priors to generate seamless, realistic, novel views from a handful of source views, while also adhering to the scene layout as seen from satellite images…
-
Which Hand Was Late? Diagnosis for Robot Failure Recovery in Bimanual Tool Use
[Robotyka] Autorzy: Baptiste Bonin, Caro Strickland, Audrey Durand Failure diagnosers for robot manipulation are increasingly vision--language models (VLMs), trained and evaluated on single-arm failures produced by perturbing a successful demonstration. Bimanual tool use adds failures of other kinds: a tool that slips out of its socket while still held, two correct gestures made at different times, and attempts that fail for two reasons at once. On a simulated bimanual tool-use task whose failure causes are read from the recorded trace, we measure what each sensing channel lets a diagnoser tell. The tool's slip is read on the tool hand; which hand was late is read on both arms, while a sensor on one hand reads its own hand's delay and at most part of the other's; and whether a late attempt was also pushed too weakly is not identifiable from passive sensing when the tool hand is late. Within two attempts, a repair policy that escalates when the cause is…
-
Ghostty 1.4
1 275 punktów · 407 komentarzy · autor deaux · ghostty.org
-
Police are using AI to pull over drivers for 'suspicious' behavior
390 punktów · 305 komentarzy · autor gumby · gizmodo.com
-
A 28-Year-Old DOGE Operative Gutted USAID. HR Had No Record of Him Working There
240 punktów · 166 komentarzy · autor ck2 · www.wired.com
-
Classification of Finite Simple Groups Formalized in Lean
236 punktów · 74 komentarze · autor pfdietz · cfsg.axiommath.ai
-
Amazon Is Gutting Its AI Division After Sustained Failure
360 punktów · 276 komentarzy · autor dpflan · futurism.com
-
New 14‑inch MacBook Pro with M6
403 punktów · 556 komentarzy · autor beex · www.apple.com
-
Magnituda 4,9 — 70 km WNW of Callaguip, Philippines
Głębokość 10 km.
-
Genie 4
986 punktów · 562 komentarze · autor acossta · deepmind.google
-
Magnituda 4,8 — south of the Fiji Islands
Głębokość 497 km.
-
Anthropic trained Claude on illegally obtained Stanford professors' books
550 punktów · 282 komentarze · autor car · stanforddaily.com
-
Magnituda 5,0 — 29 km W of Río Grande, Panama
Głębokość 10 km. Zgłoszeń od świadków: 2.
-
A $300B 'Debt Wall' Is Looming over Private-Equity Backed Companies
171 punktów · 62 komentarze · autor JumpCrisscross · www.wsj.com
-
Magnituda 5,4 — 126 km S of Pundong, Indonesia
Głębokość 10 km. Zgłoszeń od świadków: 3.
-
Magnituda 4,9 — 156 km S of Pundong, Indonesia
Głębokość 21 km.
-
Magnituda 4,6 — 41 km S of Farkhār, Afghanistan
Głębokość 115 km.
-
US Government is hiding a secret court ruling about how it spies on Americans
1 035 punktów · 412 komentarzy · autor helterskelter2 · www.wired.com
-
Is my data used for model training?
221 punktów · 111 komentarzy · autor jonpizza · privacy.claude.com
-
PHP2Shell: Exploitation attempts and remediation trends
191 punktów · 60 komentarzy · autor acossta · www.wiz.io
-
Alleged Israeli spy company targeted Starlink users
139 punktów · 31 komentarzy · autor mmaia · www.reuters.com
-
Here be monsters: What do you still need to know when agents do the work?
183 punktów · 97 komentarzy · autor adrq · blog.adrq.dev
-
New iMac with M6
348 punktów · 437 komentarzy · autor notfried · www.apple.com
-
New 14‑inch MacBook Pro with M6
165 punktów · 201 komentarzy · autor meetpateltech · www.apple.com