Knowledge catalogue
arXiv:2605.02892v1 Announce Type: new Abstract: Personalized image completion aims to restore occluded regions in personal photos while preserving identity and appearance. Existing methods either rely
This post from ComfyUI on X (Twitter) likely compares different versions or configurations of Astra 2, a model or tool within the ComfyUI ecosystem, emphasizing that the detailed results demonstrate c
arXiv:2603.14643v2 Announce Type: replace-cross Abstract: Large language models (LLMs) exhibit strong general capabilities, but their deployment in high-stakes domains is hindered by their opacity and
arXiv:2605.01229v1 Announce Type: cross Abstract: Cross-attention patterns in neural machine translation (NMT) are widely used to study how multilingual models align linguistic structure. We report a
arXiv:2507.21803v2 Announce Type: replace Abstract: Carbon Capture and Storage (CCS) stands as a pivotal technology for fostering a sustainable future. The process, which involves injecting supercriti
arXiv:2408.04596v2 Announce Type: replace Abstract: In this work, we use language modeling to investigate the factors that influence insertional code-switching. Code-switching occurs when a speaker al
Codex, likely referring to OpenAI's code generation model, is experiencing increased adoption and usage. The article from Ben's Bites discusses the growing momentum and applications of this AI coding
arXiv:2605.00908v1 Announce Type: new Abstract: This paper presents a comparative evaluation of convolutional and transformer-based object detection architectures for early weed detection in realistic
arXiv:2605.01048v1 Announce Type: new Abstract: Counterfactual prompting (i.e., perturbing a single factor and measuring output change) is widely used to evaluate things like LLM bias and CoT faithful
arXiv:2604.17450v2 Announce Type: replace Abstract: Enterprise SLM deployment faces epistemic asymmetry: small models cannot self-correct reasoning errors, while frontier LLMs incur prohibitive costs
arXiv:2603.14632v2 Announce Type: replace Abstract: The quality and realism of synthetically generated fingerprint images have increased significantly over the past decade fueled by advancements in ge
arXiv:2510.22555v2 Announce Type: replace-cross Abstract: Graph Neural Networks(GNNs) are vulnerable to backdoor attacks, where adversaries implant malicious triggers to manipulate model predictions.
arXiv:2509.25020v2 Announce Type: replace Abstract: Transformer-based models can perform complicated reasoning by generating reasoning paths token by token. While effective, this approach often requir
arXiv:2605.01236v1 Announce Type: new Abstract: Unified image restoration using a single model often faces task interference due to diverse degradations. To address this, we propose DACG-IR (Degradati
arXiv:2605.00894v1 Announce Type: new Abstract: Vision foundation models (VFMs), such as DINOv3, provide rich semantic representations that are promising for computational pathology. However, many cur
arXiv:2605.02417v1 Announce Type: new Abstract: With recent advancements in large-scale pre-trained text-to-image (T2I) models, training-free image editing methods have demonstrated remarkable success
arXiv:2605.02752v1 Announce Type: new Abstract: Open-world text-guided class-agnostic counting (CAC) has emerged as a flexible paradigm for counting arbitrary object classes by using natural language
arXiv:2605.02867v1 Announce Type: new Abstract: Despite significant advances in Reinforcement Learning (RL), model performance remains highly sensitive to algorithm and hyperparameter configurations,
arXiv:2605.02411v1 Announce Type: cross Abstract: A semantic gap separates how users describe tasks from how tools are documented. As API ecosystems scale to tens of thousands of endpoints, static ret
arXiv:2605.01199v1 Announce Type: new Abstract: Transformer-based models have achieved remarkable success across a wide range of domains, yet our understanding of their training dynamics remains limit
arXiv:2605.01367v1 Announce Type: cross Abstract: High-fidelity circuit execution on noisy intermediate-scale quantum devices is bottlenecked by compilation pipelines that disregard complex, correlate
arXiv:2605.02789v1 Announce Type: cross Abstract: Modern fuzzers increasingly use Large Language Models (LLMs) to generate structured inputs, but LLM-driven fuzzing is sensitive to prompt initializati
arXiv:2605.02108v1 Announce Type: new Abstract: Deep residual architectures are modeled as products of near-identity Jacobians. This paper proves deterministic quotient-geometric estimates for singula
Grok 4.3 Grok 4.3 is now live on the xAI API. It’s our fastest, most intelligent model to date. It tops the @ArtificialAnlys leaderboards in agentic tool calling and instruction following, and ranks #
arXiv:2504.10063v4 Announce Type: replace Abstract: Hallucination, i.e., generating factually incorrect content, remains a critical challenge for large language models (LLMs). We introduce TOHA, a TOp
arXiv:2605.01428v1 Announce Type: new Abstract: Despite significant strides in factual reliability, errors -- often termed hallucinations -- remain a major concern for generative AI, especially as LLM
arXiv:2601.17467v2 Announce Type: replace Abstract: Large reasoning models (LRMs) often generate long, seemingly coherent reasoning traces yet still produce incorrect answers, making hallucination det
arXiv:2508.12778v2 Announce Type: replace Abstract: Medical large vision-language Models (Med-LVLMs) have shown promise in clinical applications but suffer from factual inaccuracies and unreliable out
arXiv:2602.13933v2 Announce Type: replace Abstract: Large language model (LLM) agents demonstrate strong performance in short-text contexts but often underperform in extended dialogues due to ineffici
arXiv:2509.03540v3 Announce Type: replace Abstract: Large Language Models (LLMs) often struggle with producing factually consistent answers due to limitations in their parametric memory. Retrieval-Aug
arXiv:2605.00433v1 Announce Type: cross Abstract: Code generation, which aims to automatically generate source code from given programming requirements, has the potential to substantially improve soft
in japan we say “itadakimasu” before using AI tools to show gratitude to the people who provided training data, the researchers who trained the model, the entire chip supply chain, mother earth for th
arXiv:2605.01402v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) struggle with numerical regression under long-tailed target distributions. Token-level supervised fine-tuning (
In this post, you will learn how you can use Amazon Nova Foundation Models in Amazon Bedrock to apply generative AI techniques for both business protection and enhancement. You can identify obvious an
arXiv:2602.12873v4 Announce Type: replace-cross Abstract: Generative social robots (GSRs) powered by large language models enable adaptive, conversational tutoring but also introduce risks such as mis
Lambda Labs has assembled a new leadership team to develop and manage large-scale AI infrastructure capable of supporting gigawatt-level power consumption for advanced AI models. The company is positi
arXiv:2605.01957v1 Announce Type: cross Abstract: Low-dimensional projections of text embeddings support visual analysis of document collections, but their spatial organization may not reflect the rel
Release: llm-echo 0.5a0 New -o thinking 1 option to help test against LLM 0.32a0 and higher. This plugin provides a fake model called 'echo' for LLM which doesn't run an LLM at all - it's useful for w
arXiv:2601.19487v2 Announce Type: replace Abstract: Safety-aligned LLMs suffer from two failure modes: jailbreak (answering harmful inputs) and over-refusal (declining benign queries). Existing vector
arXiv:2605.01224v1 Announce Type: new Abstract: This paper argues that contemporary multilingual NLP has converged on a fragile and misleading paradigm of incidental multilingualism. Today's LLMs appe
arXiv:2605.01386v1 Announce Type: new Abstract: Large Language Models (LLMs) lack persistent memory for long-term personalized conversations. Existing graph-based memory systems suffer from informatio
arXiv:2605.01967v1 Announce Type: cross Abstract: Deploying multimodal models in real-world scenarios requires generalization to new environments where recording conditions differ from training, a cha
arXiv:2605.01369v1 Announce Type: cross Abstract: Deep learning has been widely adopted for WiFi CSI-based human activity recognition (HAR) due to its ability to learn spatio-temporal features in a pr
arXiv:2508.09193v2 Announce Type: replace Abstract: Recent advancements in generative modeling emphasize the importance of natural language as a highly expressive and accessible modality for controlli
NEW paper from Microsoft Research. Nice study on long-horizon agent generalization. (bookmark it) The team runs a study where the only variable is task horizon length. They use the same decision rules
arXiv:2605.02675v1 Announce Type: cross Abstract: This paper introduces an extension of generalised filtering for online applications. Generalised filtering refers to data assimilation schemes that jo
arXiv:2511.06838v4 Announce Type: replace-cross Abstract: The substantial memory bandwidth and computational demands of large language models (LLMs) present critical challenges for efficient inference
arXiv:2605.02730v1 Announce Type: new Abstract: Despite the success of Large-Vision Language Models (LVLMs), general optimization objectives (e.g., standard MLE) fail to constrain visual trajectories,
arXiv:2605.01948v1 Announce Type: new Abstract: Collecting diverse, high-quality manipulation data for Vision-Language-Action (VLA) model training remains prohibitively expensive for many research gro
arXiv:2512.06938v2 Announce Type: replace Abstract: Modern neural language models achieve high accuracy in text generation, yet precise control over generation length remains underdeveloped. In this p
arXiv:2605.01862v1 Announce Type: new Abstract: Offline goal-conditioned RL (GCRL) learns goal-reaching policies from static datasets, but real-world datasets are often partially observable and histor
arXiv:2605.02693v1 Announce Type: cross Abstract: Across many scientific disciplines, multiple observations are collected from the same experimental units, and in modern datasets these observations of
arXiv:2605.00893v1 Announce Type: new Abstract: Generative vision-language models can produce fluent medical image captions but remain prone to hallucination, over-specific diagnostic claims, and fact
arXiv:2605.02505v1 Announce Type: new Abstract: Semantic Role Labeling (SRL) provides an explicit representation of predicate-argument structure, capturing linguistically grounded relations such as wh
arXiv:2605.02147v1 Announce Type: new Abstract: Sampling-based model predictive control methods like MPPI and CEM are essential for real-time control of nonlinear robotic systems, particularly where d
Seedance 2.0 is an update or feature release for ComfyUI, a node-based UI for Stable Diffusion and other generative AI models. This announcement likely describes new functionality, improvements, or en
arXiv:2605.02862v1 Announce Type: new Abstract: The integration of Large Language Model (LLM) reasoning principles into classical robot path planning represents a rapidly emerging research direction.
arXiv:2604.06091v2 Announce Type: replace Abstract: Large language model (LLM) agents are increasingly acting as human delegates in multi-agent environments, where a representative agent integrates di
arXiv:2605.01708v1 Announce Type: cross Abstract: Contemporary systems serving large language models (LLMs) have adopted prefill-decode disaggregation to better load-balance between the compute-bound
arXiv:2605.01459v1 Announce Type: new Abstract: Single-Image Super-Resolution (SISR) aims to reconstruct a High-Resolution (HR) image from a Low-Resolution (LR) observation, a fundamentally ill-posed