Knowledge catalogue
In this post, we share how the AWS Generative AI Innovation Center (GenAIIC) collaborated with Works Human Intelligence (WHI) to build two AI agents using Amazon Bedrock AgentCore. We discuss the chal
This article describes how OpenAI's Codex model can be used to build autonomous tax agents capable of self-improvement through code generation and execution. The work demonstrates using large language
arXiv:2605.27082v1 Announce Type: new Abstract: Biomedical discovery often requires connecting broad biomedical knowledge with specific experimental or clinical data. Background knowledge suggests rel
arXiv:2605.26242v1 Announce Type: new Abstract: Can large language models detect and report their own internal states? A number of studies have argued that the answer to this question is yes. We argue
arXiv:2605.27243v1 Announce Type: new Abstract: Large vision-language models increasingly rely on long-context modeling to reason over documents, hour-level videos, and long-horizon agent trajectories
arXiv:2605.26820v1 Announce Type: new Abstract: Vision-language-action (VLA) models provide a promising foundation for general-purpose robotics. However, their successful deployment in real-world scen
arXiv:2605.26675v1 Announce Type: cross Abstract: CART random forests are among the most widely used modern predictive methods, with well-documented empirical success. Yet, at the mechanistic level, t
arXiv:2605.27000v1 Announce Type: cross Abstract: Repeated sampling with a verifier is the standard way to allocate test-time compute for code generation, with pass@K as the canonical metric. Yet the
arXiv:2605.27043v1 Announce Type: cross Abstract: Predictive models trained on observational data often fail to generalise to the distributions they encounter when deployed, especially when the traini
arXiv:2605.27281v1 Announce Type: new Abstract: Predicting the effect of interventions with many possible variations, e.g., therapeutic content that affects mental health outcomes or an earnings call
arXiv:2605.26679v1 Announce Type: cross Abstract: Cross-slice attack attribution in 6G networks requires identifying causal propagation chains through shared infrastructure in under 100 ms. Existing m
arXiv:2605.26774v1 Announce Type: new Abstract: Cesarean Scar Defect (CSD) is one of the most prevalent complications following cesarean delivery. Transvaginal ultrasonography is widely used for prima
arXiv:2511.14075v2 Announce Type: replace-cross Abstract: Classifier free guidance is a standard method for conditional sampling in diffusion models, but its sampling rule is not aligned with the obje
arXiv:2601.21576v2 Announce Type: replace Abstract: Chain-of-Thought (CoT) has unlocked advanced reasoning abilities of Large Language Models (LLMs) with intermediate steps, yet incurs prohibitive com
arXiv:2605.26542v1 Announce Type: cross Abstract: Tool-using agents increasingly operate in open-ended deployment environments, where they compose file systems, web APIs, code interpreters, and enterp
arXiv:2605.27146v1 Announce Type: new Abstract: Self-Supervised Learning (SSL) has emerged as a powerful paradigm to mitigate the reliance on large, annotated datasets, a common bottleneck in medical
arXiv:2605.26994v1 Announce Type: new Abstract: Charts are widely used to present complex data for analysis and decision making. Existing chart understanding benchmarks mainly focus on static charts,
arXiv:2605.27311v1 Announce Type: new Abstract: Chart question-answering (QA) benchmarks aim to pose questions that require visual reasoning to correctly answer, but models can often reach solutions t
arXiv:2605.26734v1 Announce Type: new Abstract: Existing Multi-Turn Composed Image Retrieval (MTCIR) datasets lack dialogue-history consistency and are restricted to the fashion domain. To address the
Cisco and OpenAI partnered to integrate OpenAI's Codex AI model into Cisco's enterprise engineering tools to enhance software development and automation capabilities. The collaboration aims to improve
A new report out today from Cisco Systems Inc. argues that none of the closed flagship large language models it tested can be considered safe once an attacker is allowed to push past a single prompt,
arXiv:2410.00995v3 Announce Type: replace Abstract: The automatic synthesis of analog circuits presents significant challenges. Most existing approaches formulate the problem as a single-objective opt
arXiv:2605.26310v1 Announce Type: new Abstract: The detection of unmanned aerial vehicles (UAVs) is important for the protection of civilian and military infrastructure. In this paper we propose a cos
arXiv:2502.03946v5 Announce Type: replace Abstract: Data preprocessing is often paid little attention in machine learning, despite its potentially significant impact on model performance. While automa
arXiv:2605.26483v1 Announce Type: new Abstract: Medical video diagnosis involves inferring clinical decisions from dynamic tissue responses throughout examination processes. Existing methods rely on a
arXiv:2605.26349v1 Announce Type: new Abstract: Industrial automation is at a pivotal moment, as Physical AI is driving a transition from rigid, hand-engineered automation systems toward more flexible
arXiv:2601.09886v2 Announce Type: replace Abstract: How predictable a word is can be quantified in two ways: using human responses to the cloze task or using probabilities from language models (LMs).W
arXiv:2605.26524v1 Announce Type: cross Abstract: Maritime intelligent transportation systems (MITS) are essential for ensuring navigation safety and efficiency in busy waterways. However, accurate ve
arXiv:2605.26294v1 Announce Type: new Abstract: Skin cancer is a common and fast rising malignancy worldwide. Early detection is critical for improving outcomes. Deep learning models trained on dermos
arXiv:2605.26192v1 Announce Type: cross Abstract: Protein structure generative models excel at predicting single protein static structures from sequence, but routinely fail to capture the correct conf
Co-founder and Head of Design at Replit, @HayaOdeh shapes the brand, user experience, and product design of one of the world’s most accessible vibe coding platforms. See her take the stage on day two
arXiv:2605.26967v1 Announce Type: new Abstract: Existing video captioning methods struggle to balance visual fidelity and redundancy: holistic captions are compact but lose fine-grained evidence, wher
Cogent Security Inc., a startup that employs agentic artificial intelligence for vulnerability management, today launched two new platform capabilities aimed at compressing enterprise vulnerability re
cognition is now the largest independent agent lab in the world. take the 200% utilization that everyone is hitting from this chart and run out the sales growth from this, i encourage you to go thru t
arXiv:2605.26304v1 Announce Type: new Abstract: Collaborative navigation of heterogeneous robots in unknown environments poses significant challenges due to sensing, communication, and computational l
arXiv:2604.03785v2 Announce Type: replace Abstract: Communication is essential for coordination in cooperative multi-agent reinforcement learning under partial observability, yet cross-timestep delays
arXiv:2605.26475v1 Announce Type: cross Abstract: Vision-based metric distance and area measurement remains challenging in large-scale outdoor environments due to long-range sensing, camera zoom, and
arXiv:2603.07211v2 Announce Type: replace Abstract: Direct Preference Optimization (DPO) has become a standard framework for safety alignment, but its reliance on pairwise preference updates makes tra
Completely agree, @hwchase17 ! This is the meta-level breakthrough we've all been waiting for. Self-optimizing loops finally feel production-ready because LangSmith Engine turns evaluation from a manu
completing the loop is paramount most unrecognized step in the development lifecycle is iteration on the process itself everyone is talking about self-optimizing loops in software & agents. but what d
arXiv:2605.26657v1 Announce Type: new Abstract: Long-horizon decision problems with cumulative damage couple locally attractive actions to globally adverse outcomes. We identify two orthogonal failure
arXiv:2605.26789v1 Announce Type: new Abstract: Post-training is routinely evaluated through aggregate benchmark scores that treat multi-hop reasoning as a single capability -- as if a model that answ
Computer use in Fleet is now in public beta! You can now give your agents in Fleet access to secure virtual machines allowing them to own engineering tasks for you. Use these via Fleet agents in the U
arXiv:2509.04632v2 Announce Type: replace-cross Abstract: Large collections of tabular data from data lakes, web tables and open data portals often originate from heterogeneous sources, leading to rep
arXiv:2605.26537v1 Announce Type: new Abstract: Language Models (LMs) emit Chains-of-Thought (CoTs) that drive much of their capability. However, the same sequence that carries useful reasoning can al
arXiv:2605.26413v1 Announce Type: cross Abstract: Understanding the effects of interventions is central to scientific progress, with randomized controlled trials (RCTs) regarded as the gold standard f
arXiv:2605.26990v1 Announce Type: cross Abstract: Bayesian experimental design (BED) is a principled framework for data-efficient design of sequential experiments. However, existing BED methods are un
arXiv:2601.21845v2 Announce Type: replace Abstract: Meta reinforcement learning (RL) allows agents to leverage experience across a distribution of tasks on which the agent can train at will, enabling
arXiv:2605.26279v1 Announce Type: new Abstract: Constraint Acquisition (CA) and related research on the validation and enhancement of Mathematical Programming (MP) models from domain knowledge artifac
arXiv:2602.10450v2 Announce Type: replace-cross Abstract: Optimization modeling underpins decision-making in logistics, manufacturing, energy, and finance, yet translating natural-language requirement
arXiv:2605.26827v1 Announce Type: cross Abstract: Recent benchmarks reveal that despite strong reasoning capabilities, large language models (LLMs) still struggle to faithfully apply complex contextua
arXiv:2009.11997v3 Announce Type: replace-cross Abstract: Effective planning in model-based reinforcement learning (MBRL) and model-predictive control (MPC) relies on the accuracy of the learned dynam
arXiv:2605.25569v2 Announce Type: replace Abstract: Existing deep learning-based low-light enhancement methods are typically trained on limited datasets with single enhancement targets, which restrict
arXiv:2605.26440v1 Announce Type: new Abstract: The rapid advancement of Large Language Models (LLMs) has outpaced the scalability of traditional evaluation benchmarks, which remain heavily dependent
arXiv:2605.27051v1 Announce Type: cross Abstract: Formal verification of large C programs is impeded by state-space explosion: Bounded Model Checking (BMC) tools must encode the entire state space up
arXiv:2605.26977v1 Announce Type: new Abstract: The Muon optimizer has recently demonstrated remarkable empirical success in training large language models. However, the theoretical understanding of i
This post highlights an open-source project built using LangChain and Langgraph that implements thoughtful memory management and organization features. The project demonstrates best practices for stru
arXiv:2605.26754v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) increasingly underpins high-stakes applications, yet remains vulnerable to Confundo-style poisoning where adversa
arXiv:2605.26595v1 Announce Type: cross Abstract: Large language models (LLMs) are often fine-tuned on uncurated text datasets that adversaries can poison. Existing poisoning attacks primarily rely on
arXiv:2601.22519v2 Announce Type: replace-cross Abstract: Discrete flow models (DFMs) have been proposed to learn the data distribution on finite state space, offering a flexible framework as an alter