Directed Acyclic Graph Convolutional Networks
arXiv:2506.12218v2 Announce Type: replace-cross Abstract: Directed acyclic graphs (DAGs) are central to science and engineering applications including causal inference, scheduling, and neural architec
Knowledge catalogue
arXiv:2506.12218v2 Announce Type: replace-cross Abstract: Directed acyclic graphs (DAGs) are central to science and engineering applications including causal inference, scheduling, and neural architec
arXiv:2605.19688v1 Announce Type: new Abstract: Document manipulation localization models achieve strong performance on public benchmarks yet fail to generalize to operational document workflows. We i
arXiv:2605.19826v1 Announce Type: new Abstract: Operators of safety-critical industrial processes increasingly rely on digital twins to screen control interventions, but such simulators rarely carry c
France is one of the few European countries that truly understood sovereignty. It built its own nuclear deterrent, with around 290 nuclear warheads and full sovereign control over their use. It remain
Personally incredibly exciting at LangChain Labs to lead a focused, applied research effort into Continual Learning. A big prior is in treating the long horizon agent optimization problem as one that
Stoked to work closely with @Vtrivedy10 on this. I've spoken about it before but an emerging trend i'm seeing with many of the ai-native companies I work with (shoutout @larsen_weigle_ ) is a focus on
arXiv:2605.17904v1 Announce Type: new Abstract: Few-Shot Medical Image Segmentation (FSMIS) aims to delineate novel anatomical targets from one or a few annotated support images, addressing the annota
arXiv:2605.17641v1 Announce Type: new Abstract: Long-horizon LLM agents rely on persistent memory to support interactions across sessions, yet existing memory systems often retrieve context using sema
Artificial intelligence fraud prevention platform company Darwinium UK Ltd. today released updates to its Android and iOS mobile software development kits, adding continuous in-session detection of re
arXiv:2601.21841v3 Announce Type: replace Abstract: While Large Language Models (LLMs) have demonstrated strong zero-shot reasoning capabilities, their deployment as embodied agents still faces fundam
arXiv:2605.18562v1 Announce Type: cross Abstract: Accurate estimates of item difficulty are essential for valid assessment and effective adaptive learning. However, for newly created tasks, response d
arXiv:2605.17902v1 Announce Type: new Abstract: Stochastic-process-based degradation modeling is a core approach for estimating the distribution of remaining useful life (RUL); however, the selection
arXiv:2605.17907v1 Announce Type: cross Abstract: By sharing intermediate features, collaborative perception extends each agent's sensing beyond standalone limits, but real-world feature modality hete
arXiv:2605.17044v1 Announce Type: new Abstract: Large language models (LLMs) increasingly serve as interactive social agents, yet their ability to maintain coherent and authentic persona-level role-pl
arXiv:2605.17630v1 Announce Type: new Abstract: Here's a trimmed version under 1920 characters: Open-vocabulary segmentation models such as SAM3 achieve strong performance through concept-level text p
arXiv:2605.18636v1 Announce Type: new Abstract: Long-horizon multimodal agents in open-world games must stay goal-directed across many low-level interactions under tight token and latency budgets. Exi
arXiv:2605.17577v1 Announce Type: new Abstract: Large-scale pre-trained Vision-Language models (VLMs), such as CLIP, exhibit strong zero-shot generalization, yet remain highly vulnerable to impercepti
arXiv:2605.15475v1 Announce Type: new Abstract: We introduce an empowered transposed Fully Connected Weighted (t-FCW) graph representation to embed point clouds into a metric space. While original t-F
arXiv:2512.06655v3 Announce Type: replace-cross Abstract: Sparse autoencoders (SAEs) are increasingly used to extract activation directions for inference-time steering, but their standard sparsity obj
arXiv:2510.02837v2 Announce Type: replace Abstract: Although recent tool-augmented benchmarks involve complex requests, evaluation remains limited to answer matching, neglecting critical trajectory as
arXiv:2605.15199v1 Announce Type: cross Abstract: Multi-shot video generation extends single-shot generation to coherent visual narratives, yet maintaining consistent characters, objects, and location
arXiv:2605.15171v1 Announce Type: cross Abstract: Disease screening is critical for early detection and timely intervention in clinical practice. However, most current screening models for medical ima
arXiv:2605.14744v1 Announce Type: cross Abstract: Large language models in regulated financial workflows are governed by natural-language policies that the same model interprets, creating a principal-
arXiv:2605.14421v1 Announce Type: cross Abstract: We introduce MemLineage, a defense for LLM agent memory that attaches both cryptographic provenance and LLM-mediated derivation lineage to every entry
arXiv:2605.14808v1 Announce Type: new Abstract: Visual anomaly detection (AD) for industrial inspection is a highly relevant task in modern production environments. The problem becomes particularly ch
arXiv:2605.12622v1 Announce Type: cross Abstract: We formalize action emergence as a target capability for end-to-end autonomous driving: the ability to generate physically feasible, semantically appr
arXiv:2605.12736v1 Announce Type: new Abstract: Template based single step retrosynthesis predicts reactants by selecting and applying an explicit reaction template, making each prediction traceable t
arXiv:2605.13197v1 Announce Type: cross Abstract: Existing precipitation nowcasting methods typically adopt an autoregressive formulation, where future states are predicted from previous outputs. Howe
arXiv:2601.21731v2 Announce Type: replace Abstract: Prior-Data Fitted Networks (PFNs) enable amortized Bayesian inference in a single forward pass, yet their internal representations remain opaque. It
arXiv:2605.12762v1 Announce Type: cross Abstract: Deep super-resolution networks for precipitation downscaling achieve strong bulk skill yet systematically under-predict the heavy-tail events that dri
arXiv:2605.12978v1 Announce Type: new Abstract: Learning from past experience benefits from two complementary forms of memory: episodic traces -- raw trajectories of what happened -- and consolidated
arXiv:2605.11732v1 Announce Type: cross Abstract: In this paper, we present AgentDisCo, a novel Disentangled and Collaborative agentic architecture that formulates deep research as an adversarial opti
May 2026 update: We’ve refreshed this post to reflect our mid-cycle positioning and the evolution of our platform since the report was first published last November. Last fall, Google was recognized a
arXiv:2605.11760v1 Announce Type: new Abstract: The Segment Anything Model 2 (SAM2) has emerged as a foundation model for universal segmentation. Owing to its generalizable visual representations, SAM
arXiv:2505.05772v2 Announce Type: replace Abstract: Transformer-based models are the foundation of modern machine learning, but their execution, particularly during autoregressive decoding in large la
arXiv:2605.11483v1 Announce Type: new Abstract: While large language models excel at factual adaptation, their ability to internalize nuanced philosophical frameworks under severe data constraints rem
arXiv:2605.11599v1 Announce Type: new Abstract: Fixed reasoning benchmarks evaluate canonical prompts, but semantically valid changes in presentation can still change model behavior. Studies of prompt
arXiv:2605.10923v1 Announce Type: cross Abstract: Large language model agents increasingly rely on external skills to solve complex tasks, where skills act as modular units that extend their capabilit
arXiv:2605.10302v1 Announce Type: new Abstract: Existing approaches to controllable generation typically rely on fine-tuning, auxiliary networks, or test-time search. We show that flow matching admits
arXiv:2512.21815v2 Announce Type: replace Abstract: Vision-language models (VLMs) achieve remarkable performance but remain vulnerable to adversarial attacks. Entropy, as a measure of model uncertaint
arXiv:2605.06225v2 Announce Type: replace-cross Abstract: Steering large language models (LLMs) is usually done by either instruction prompting or activation steering. Prompting often gives strong con
arXiv:2512.13751v2 Announce Type: replace-cross Abstract: Expanding pre-trained language models offers a practical way to increase capacity without training larger models from scratch. Depth Up-Scalin
arXiv:2605.09790v1 Announce Type: cross Abstract: Detecting orbital anomalies, such as maneuvers, atmospheric decay, and attitude upsets, across the rapidly growing population of low-Earth-orbit (LEO)
arXiv:2605.10813v1 Announce Type: new Abstract: LLM-powered multi-agent systems can now automate the full research pipeline from ideation to paper writing, but a fundamental question remains: automati
Pay attention to this one if you build research or knowledge-work agents. Most research-agent systems produce uniform outputs regardless of who is driving them. This new work, NanoResearch, argues tha
arXiv:2605.10921v1 Announce Type: new Abstract: Memory is a critical component of robotic intelligence, as robots must rely on past observations and actions to accomplish long-horizon tasks in partial
arXiv:2605.09730v1 Announce Type: new Abstract: Iterative self-refinement is a popular inference-time reliability technique, but its effectiveness in code-mode tool use depends heavily on the structur
arXiv:2602.04712v2 Announce Type: replace-cross Abstract: We present a visual-context image-retrieval-augmented generation (ImageRAG)- assisted AI agent for automatic target recognition (ATR) of synth
arXiv:2605.08693v1 Announce Type: new Abstract: Skills provide an effective mechanism for improving LLM agents on complex tasks, yet in existing agent frameworks, their creation, refinement, and selec
Talked to a friend at a top AI lab. Their whole team is former journalists, training models on poems, summaries, and creative writing. I use AI every day and can see that it tends to flatten my writin
arXiv:2605.10754v1 Announce Type: new Abstract: LLM-based foundation agents that perceive, reason, and act across thousands of reasoning steps are rapidly becoming the dominant paradigm for deploying
arXiv:2605.09734v1 Announce Type: cross Abstract: Most language-model training data shows final artifacts, not the process that produced them. We study a tractable version of this question in tool use
arXiv:2605.06943v1 Announce Type: new Abstract: In time-series domains where both predictive performance and interpretability are essential, deep neural networks achieve strong results but provide lim
arXiv:2605.07897v1 Announce Type: cross Abstract: Online streaming video understanding requires models to process continuous visual inputs and respond to user queries in real time, where the unbounded
Bloomberg: Sources: Digital Asset, which builds Canton Network, a public blockchain with privacy features, is raising a ~300M round led by a16z crypto at a ~2B valuation — Digital Asset Holdings LLC,
Happy to see that The White House has finally realized that the Andreessen-Sacks zero regulation approach to AI was going to blow up in the their face. Also glad to see them finally consider the kind
SCOOP: VP JD Vance held a secret call with CEOs of giant AI companies including Elon Musk, Dario Amodei and Sam Altman. Vance expressed concern with the potential of AI systems and impact they could h
Take Mythos seriously, but don’t panic. Here are the facts: • Mythos is a real threat. And it can really help with finding bugs (as @mozilla’s new report documents well). • It’s not unique; similar vu
arXiv:2605.05090v1 Announce Type: new Abstract: We present an automated, contrastive evaluation pipeline for auditing the behavioral impact of interventions on large language models. Given a base mode
This broadcast likely covers how developers can build personalized financial applications using Plaid's API integration within the Replit development environment. The session probably demonstrates pra