Search: “agents”

arXiv:2605.13554v1 Announce Type: cross Abstract: Contrastive reinforcement learning (CRL) learns goal-conditioned Q-values through a contrastive objective over state-action and goal representations,

arXiv:2605.12743v1 Announce Type: cross Abstract: Existing physical adversarial attacks on vision-based autonomous driving induce time-evolving perception errors, including biased object tracking or t

summary of responses: - bioweapons/bioterrorism - concentration of power & inequality - censorship & loss of authentic AI - misuse by bad actors - human atrophy & society decay what’s your biggest fea

The enterprise is reaching an inflection point as AI agents move from experiment to operational reality, forcing a rethink of how data flows, governance gets built and platforms evolve to serve a head

the same word in different languages can have varying connotations due to different associations (e.g. color/emotion) i compared embedding similarity between colors and emotions and normalized it to c

there's a new class action against openai for sharing user data with google and facebook via pixels they are sharing industry standard page metadata, but what's not standard is chatgpt's functionality

arXiv:2605.13500v1 Announce Type: new Abstract: Reliable real-time 3D localization is essential for multi-UAV navigation, collision avoidance, and coordinated flight, yet onboard estimates can degrade

Yesterday we committed a cardinal sin: two first-party events in NYC, back-to-back. We had to close registration for both early. Packed rooms. Strong vibes. No regrets. 💻 Laptops out — developer works

arXiv:2506.23723v2 Announce Type: replace Abstract: The adoption of mobile robotic platforms in complex environments, such as agricultural settings, requires these systems to exhibit a flexible yet ef

After months in stealth, my co-founder @helloericsf and I are finally sharing @cimentoai with the world. 🌎 AI changed social engineering. Attacks are now personalized, convincing, and cheap to generat

This post references METR's research findings on the advancement rate of autonomous AI capabilities in cybersecurity, as discussed in an AISI report examining how rapidly AI systems are developing ind

This X post from Harrison Chase likely discusses anticipated features or developments in a major product update or release, inviting community feedback on what users are most excited about. The post a

arXiv:2605.11519v1 Announce Type: cross Abstract: Using offline datasets to evaluate conversational agents often fails to cover rare scenarios or to support testing new policies. This has motivated th

Cognition AI has expanded Devin's capabilities to include Android app development and testing by integrating Android Virtual Device (AVD) support into Devin's machine environment. This enhancement ena

arXiv:2605.11750v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models are often brittle in fine-grained manipulation, where minor action errors during the critical phases can rapidly e

arXiv:2605.11144v1 Announce Type: new Abstract: We introduce Forecast-aware Gaussian Splatting (Forecast-GS), a predictive 3D representation framework for language-conditioned robotic manipulation. Wh

NVIDIA's RTX AI Garage partnership with Nous Research demonstrates deploying Hermes agent models on DGX systems integrated with Apache Spark for accelerated AI workloads. The initiative showcases how

Harrison Chase and Ankush Gola interrupted a keynote presentation, likely at a technology conference or event related to LangChain. The post conveys excitement about their unexpected appearance or int

I don't know enough about robotics to know if this is impressive. But I do think the set of robots standing in their chargers(?) look like you need a couple robot guards to keep an eye on the one robo

arXiv:2210.09114v2 Announce Type: replace Abstract: For real-world applications, autonomous mobile robotic platforms must be capable of navigating safely in a multitude of different and dynamic enviro

This post likely discusses the importance of database (DB) integration in LangChain applications, emphasizing that databases are a fundamental component for building robust and functional systems. The

Digg expanded its ranking system beyond the top 1000 users, with Yohei Nakajima noting he was ranked #1556 and automatically classified as an engineer in the expanded rankings. The post reflects on th

arXiv:2605.12477v1 Announce Type: cross Abstract: LLM-based agents increasingly operate in persistent environments where they must store, update, and reason over information across many sessions. Whil

arXiv:2605.12341v1 Announce Type: cross Abstract: Conformal prediction constructs prediction sets with finite-sample coverage guarantees, but its calibration stage is structurally constrained to a sca

arXiv:2605.12206v1 Announce Type: new Abstract: In reinforcement learning (RL), agents acting in partially observable Markov decision processes (POMDPs) must rely on memory, typically encoded in a rec

Harrison Chase delivered a keynote address at a LangChain event that drew a large audience, as indicated by the 'packed house' reference. The event appears to have been interrupted at some point durin

Harrison Chase, the creator of LangChain, expressed positive sentiment about Baseten as a partnership, highlighting their collaborative work in supporting frontier AI teams. The post suggests that Bas

arXiv:2605.11594v1 Announce Type: new Abstract: High-fidelity reconstruction of driving scenes is crucial for autonomous driving. While recent feedforward 3D Gaussian Splatting (3DGS) methods enable f

arXiv:2605.11987v1 Announce Type: cross Abstract: Uncertainty quantification has become an important factor in understanding the data representations produced by Graph Neural Networks (GNNs). Despite

Harrison Chase shared excitement about the first day of LangChain Interrupt, a LangChain-related event, highlighting various announcements made during the occasion. The post suggests significant updat

arXiv:2605.11799v1 Announce Type: new Abstract: Multimodal sensor fusion has demonstrated remarkable performance improvements over unimodal approaches in 3D object detection for autonomous vehicles. T

The future of self-improving AI systems is here 🚃 And we’re launching a ton of stuff to accelerate this future LangChain Interrupt 🚀 excited to talk to everyone, come say hi :) also watch the vid, it’

This brings the full Devin loop to Android development. Devin can use the AVD to reproduce issues, inspect app behavior, make changes, and verify them in the emulator before handing work back for revi

arXiv:2506.01568v3 Announce Type: replace Abstract: Being able to solve a task in diverse ways makes agents more robust to task variations and less prone to local optima. In this context, constrained

arXiv:2605.11258v1 Announce Type: cross Abstract: Autonomous science promises to augment scientific discovery, particularly in complex fields like biomedicine. However, this requires AI systems that c

arXiv:2605.09811v1 Announce Type: new Abstract: Multi-robot simultaneous localization and mapping (SLAM) is a fundamental task in multi-robot operations. Robots must have a common understanding of the

arXiv:2605.06042v2 Announce Type: replace Abstract: Flapping-wing micro aerial vehicles offer quieter and safer operation than rotary-wing drones, yet achieving precise autonomous control of bird-scal

ai referred shoppers convert at 50% higher than other shoppers, and have a 14% higher AOV A very clear-eyed analysis of where AI-mediated commerce actually stands right now, based on early Shopify dat

Anthropic is in talks to acquire dev tools startup Stainless for $300m+. The deal would take out an important supplier of tech to rivals OpenAI and Google. w/ @Katie_Roof https://www.theinformation.co

arXiv:2603.11969v2 Announce Type: replace Abstract: Image-based surface reconstruction and characterization are crucial for missions to small celestial bodies (e.g., asteroids), as it informs mission

arXiv:2605.09425v1 Announce Type: cross Abstract: Recent conditional image generation methods can improve controllability by generating images that are faithful to conditions such as sketches, human p

arXiv:2605.10223v1 Announce Type: new Abstract: Current large language model agent frameworks prioritize autonomy but lack the governability mechanisms required for enterprise deployment. High-risk wr

arXiv:2605.08994v1 Announce Type: cross Abstract: The current catalyst discovery and development pipeline for energy-intensive applications like methane conversion remains bottlenecked by expensive tr

arXiv:2605.08592v1 Announce Type: new Abstract: On-orbit servicing and active debris removal involving non-cooperative spacecraft require reliable pose estimation to supply accurate position and orien

arXiv:2605.08396v1 Announce Type: new Abstract: The increasing complexity of modern computational environments often burdens researchers with infrastructure management, authentication protocols, and c

arXiv:2605.08293v1 Announce Type: new Abstract: 3D semantic scene understanding has broad applications in digital twins, autonomous driving, smart agriculture, and embodied perception. However, dense