Multi-Agent Route Planning as a QUBO Problem
arXiv:2602.07913v2 Announce Type: replace Abstract: Multi-Agent Route Planning considers selecting vehicles, each associated with a single predefined route, such that route-level coverage utility is m
Knowledge catalogue
arXiv:2602.07913v2 Announce Type: replace Abstract: Multi-Agent Route Planning considers selecting vehicles, each associated with a single predefined route, such that route-level coverage utility is m
arXiv:2508.02425v2 Announce Type: replace-cross Abstract: In physical human-robot collaboration (pHRC) settings, humans and robots collaborate directly in shared environments. Robots must analyze inte
arXiv:2105.09254v4 Announce Type: replace-cross Abstract: In many applications, researchers are interested in the direct and indirect causal effects of a treatment or exposure on an outcome of interes
arXiv:2606.30509v1 Announce Type: new Abstract: Matrix factorization (i.e., problems of the form min_{mathbf{P},mathbf{Q}} |mathbf{M}^star - mathbf{P}^opmathbf{Q}|_F^2) is a minimal learning problem t
my process for writing right now is to do some engineering work, talk to a bunch of people about it, brainstorm and research with Claude, write a post, give 1 or 2 talks on it, rewrite the post, give
arXiv:2606.29824v1 Announce Type: cross Abstract: While Large Language Models (LLMs) excel as static solvers, transforming them into autonomous agents remains challenging. This transition requires con
// Neural procedural memory // Good paper on agent memory beyond prompt retrieval. NPM stores procedural skills as activation steering vectors distilled from contrastive historical experience. Textual
arXiv:2606.30067v1 Announce Type: cross Abstract: We introduce Neural Subspace Reallocation (NSR), which reframes continual learning as memory management over parameter subspaces. Instead of treating
Notes (and a Pelican) on Claude Sonnet 5 - the new tokenizer makes it ~1.4x more expensive for English, ~1.33x more expensive for Spanish but roughly the same price for Simplified Mandarin https://sim
On FrontierCode (Extended), our benchmark for real-world engineering tasks that grades mergeability and quality, Sonnet 5 scores 53.8% and has a 57.6% pass rate (higher than Opus 4.8). Note: These rel
arXiv:2606.28413v1 Announce Type: cross Abstract: A mesh of sovereign agents has no center: no shared clock, no shared model, and no coordinator to gather data or retrain. Its competence rests on each
arXiv:2606.29238v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) eliminates the learned critic in PPO by using the mean reward of grouped rollouts as a baseline. We provide a
arXiv:2606.30077v1 Announce Type: cross Abstract: With Large Language Model (LLM) pre-training and fine-tuning shifting its focus from data volume to data quality, quality data selection has emerged a
arXiv:2606.30625v1 Announce Type: cross Abstract: Contrastive embedding models trained with scale-invariant losses are typically paired with distance metrics like cosine similarity, effectively ignori
arXiv:2606.29537v1 Announce Type: new Abstract: Existing computer-use benchmarks fail to capture the realism, complexity, and long-horizon demands of real-world computer use, limiting their ability to
arXiv:2606.29272v1 Announce Type: new Abstract: Technology computer-aided design (TCAD) semiconductor device simulation is fundamentally constrained by the high computational cost of iteratively solvi
Perforce Software Inc. today expanded its Perforce Intelligence lineup with an agentic gateway for managing artificial intelligence agents, an autonomous testing platform driven by natural language an
arXiv:2606.28845v1 Announce Type: new Abstract: Personalizing Multimodal Large Language Models (MLLMs) aims to recognize users' unique concepts from visual data and provide personalized responses. Alt
Pie Tech Inc., a startup using artificial intelligence to provide growth tools for small businesses, today officially launched with an announcement that it has raised 19.5 million in new funding to ex
arXiv:2606.29225v1 Announce Type: new Abstract: LLM agents handle user requests on behalf of organizations through tool calls and must follow the company policies stated in their system prompts. Prior
arXiv:2606.29159v1 Announce Type: new Abstract: Offline root-cause-analysis (RCA) benchmarks commonly rank methods by a single pooled top-1 accuracy across multiple subsystems, and engineers often rea
arXiv:2606.28433v1 Announce Type: new Abstract: One goal in reinforcement learning (RL) research is to understand general-purpose sequential decision-making, using benchmark simulators as a proxy for
arXiv:2508.06482v2 Announce Type: replace-cross Abstract: Humans communicate with increasing efficiency in multi-turn interactions, by adapting their language and forming ad-hoc conventions. In contra
arXiv:2606.29169v1 Announce Type: cross Abstract: Many important games have more than two players and imperfect information. Existing approaches for computing Nash equilibrium, the central game-theore
arXiv:2606.29544v1 Announce Type: cross Abstract: We present Proteus, a framework developed at Resemble AI for automated robustness testing of our audio deepfake detection system. Given a detector, Pr
Qwen publishes new work on RL coding agents. (bookmark it) The idea is to continually build a verification system that co-evolves with AI agents. LLMs suffer from all sorts of reward hacking issues. T
arXiv:2606.29440v1 Announce Type: new Abstract: Repeatedly solving parametric PDEs is essential for uncertainty quantification, design optimization and inverse problems, but conventional neural operat
arXiv:2606.28627v1 Announce Type: cross Abstract: The cart-pole swing-up is a canonical benchmark for nonlinear control of underactuated systems, yet an end-to-end guarantee linking the global swing-u
This post links to a full interview with Aidan Gomez conducted by the Aston Martin F1 team, published on their official website under their 'Perspectives' feature section. The interview likely covers
arXiv:2606.28374v1 Announce Type: new Abstract: LLM agents are increasingly improved without weight updates by evolving a natural-language artifact, such as reflections, workflows, playbooks, cheatshe
arXiv:2606.30294v1 Announce Type: new Abstract: Live product demonstrations are a recurring, high-cost activity in software organizations: a human presenter must select features, dispatch the correspo
arXiv:2606.30139v1 Announce Type: new Abstract: Relevance is not permission. Attention lets a model read key-value items related to the current query, but it does not guarantee that the value contribu
arXiv:2606.30304v1 Announce Type: cross Abstract: This paper presents preliminary findings from a UKRI-funded Metascience project comparing three LLM-based approaches, GPT-4o, Mistral, and a bespoke a
arXiv:2606.29083v1 Announce Type: cross Abstract: Koopman theory promises linear structure in nonlinear dynamics, but numerical Koopman spectra are easy to compute and hard to trust. A finite EDMD mat
arXiv:2606.29649v1 Announce Type: new Abstract: Large Vision-Language Models (VLMs) are increasingly deployed as content moderation tools, yet they remain vulnerable to jailbreak attacks in which harm
arXiv:2606.29807v1 Announce Type: cross Abstract: Recent studies have shown that semantic watermarks, which embed information into the initial noise of latent diffusion models (LDMs), are vulnerable t
arXiv:2606.30611v1 Announce Type: new Abstract: Understanding facial expressions in videos requires modeling subtle and localized facial dynamics under unconstrained conditions. Although recent Vision
arXiv:2606.29867v1 Announce Type: cross Abstract: Deep Reinforcement Learning (DRL) has achieved significant success in robotics and autonomous systems, yet remains vulnerable to adversarial perturbat
arXiv:2606.30408v1 Announce Type: new Abstract: Homography estimation, as one of the fundamental problems in computer vision, remains challenged by scale variation scenarios where image pairs potentia
arXiv:2606.30384v1 Announce Type: new Abstract: Training in artificial neural networks can be viewed as a trajectory evolving through a high-dimensional loss landscape. However, the large number of tr
arXiv:2506.00400v4 Announce Type: replace-cross Abstract: LLM-based prompt optimization, which uses LLM-provided ``textual gradients'' (feedback) to refine prompts, has emerged as an effective method
arXiv:2409.00654v2 Announce Type: replace Abstract: We introduce Seed-to-Seed Translation (StS), a novel approach that combines GANs and diffusion models (DMs) for unpaired Image-to-Image Translation.
arXiv:2606.29178v1 Announce Type: new Abstract: When does retention matter for memory-augmented LLM agents? We study this with TraceRetain, a lightweight framework for bounded external memory in froze
SEO Agent. Security Agent. Design in Claude. Replit Desktop. Shopify on Replit. Skills + Custom Instructions. 450+ integrations. Package Firewall. And more! ✨ All shipped in June! 🤯 And there's a good
arXiv:2606.18438v2 Announce Type: replace-cross Abstract: In this paper, we study a sequential workforce management problem in a contingent labor setting with uncertainty in both worker production and
arXiv:2606.30613v1 Announce Type: new Abstract: We present Sequential Planning via Anchored Robotic Keypoints, SPARK, a training-free neurosymbolic manipulation system that reaches 43.7% on six LIBERO
arXiv:2606.28626v1 Announce Type: new Abstract: Sign language translation (SLT) remains challenging due to its high spatio-temporal complexity, long sequences, and the need to model multiple articulat
arXiv:2606.30101v1 Announce Type: cross Abstract: Existing robot policies based on learned visual embeddings lack explicit structure and are sensitive to visual distractions. Thus, the representations
arXiv:2606.30481v1 Announce Type: cross Abstract: Current large language models are extraordinary statistical engines. They compress vast amounts of text into useful patterns and can explain science,
arXiv:2602.02472v2 Announce Type: replace-cross Abstract: Progressive Learning (PL) reduces pre-training computational overhead by gradually increasing model scale. While prior work has extensively ex
arXiv:2606.28486v1 Announce Type: cross Abstract: The emergence of low-dimensional structures in the spectra of neural network weight matrices is a common empirical feature of trained models, but the
arXiv:2606.29957v1 Announce Type: cross Abstract: Most coding-agent benchmarks are static: an agent receives a complete task description up front and is judged only by its final code. Real coding assi
Thank you to everyone to came to the Claude managed agents workshop at @aiDotEngineer with @gcemaj and I. We had an absolute blast sharing our journey and walking you through building your first agent
arXiv:2601.15251v2 Announce Type: replace Abstract: Large language models (LLMs) have achieved impressive proficiency in basic arithmetic, rivaling human-level performance on standard numerical tasks.
arXiv:2606.29451v1 Announce Type: new Abstract: Self-supervised learning (SSL) pretrained models have become a dominant paradigm for visual representation learning, but they are vulnerable to backdoor
This post likely showcases visual examples or commentary on the aesthetic appearance and fit of low-rise pants, a fashion trend that was particularly popular in the early 2000s and has experienced per
Thrilled to announce the Wearable AI Workshop at ECCV 2026 🎉 that we're organizing with an awesome group of folks across Meta Reality Labs, AMI Labs, HKUST, Georgia Tech, UCF, and U. of Edinburgh. If
Claude Sonnet 5 will consume approximately 30% less API quota than Sonnet 4.6 when used through Devin Desktop or CLI until August 31, after which both models will use equivalent quota allocations. Thi
arXiv:2606.28425v1 Announce Type: cross Abstract: Increasingly autonomous agentic AI systems pose novel multi-agent risks, such as secret collusion via covert communication channels. The natural defen
arXiv:2606.30316v1 Announce Type: new Abstract: This paper studies Reinforcement Learning as an online controller for curtailment-aware workload shifting in wind-turbine-integrated high-performance co