Knowledge catalogue
arXiv:2609.18005v1 Announce Type: new Abstract: Large language model optimization is an active research area, spanning quantization of model weights, early-exit methods for skipping layers, and specul
arXiv:2509.19276v2 Announce Type: replace-cross Abstract: Solving ill-posed inverse problems requires powerful and flexible priors. We propose leveraging pretrained latent diffusion models for this ta
arXiv:2609.17565v1 Announce Type: new Abstract: Online handwriting recognition systems typically represent pen trajectories through fixed-length Euclidean shape descriptors that capture the spatial ou
arXiv:2609.18057v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has significantly improved the reasoning capabilities of large vision-language models (LVLMs). How
arXiv:2609.18849v1 Announce Type: cross Abstract: An agentic request spends substantial wall-clock time waiting for tools, and its KV cache holds GPU memory the whole time. Serving systems decide whet
arXiv:2609.18864v1 Announce Type: cross Abstract: Privacy evaluations of tool-using LLM agents often inspect a designated action, final response, or attacker report. These local proxies can miss unaut
arXiv:2609.17943v1 Announce Type: cross Abstract: Long-context LLM inference is bottlenecked by attention, whose repeated KV-cache reads make decoding memory-bound. Self-speculative decoding alleviate
arXiv:2609.18320v1 Announce Type: new Abstract: Large Language Models (LLMs) frequently exhibit hallucinations, presenting a major barrier to reliability in complex reasoning tasks. While traditional
arXiv:2609.17923v1 Announce Type: new Abstract: Sports highlight detection aims to identify the most exciting and meaningful moments from long sports videos. While existing methods often emphasize vis
Hey all, Henry from Cactus Compute here, I kinda wanted to share our latest model and get feedback from the family :) Needle 3 is a small foundation model for automation: you give it the functions you
arXiv:2609.18554v1 Announce Type: new Abstract: Multiresolution hash encodings have recently enabled fast and high-fidelity implicit neural representations by storing multi-scale features in fixed-siz
arXiv:2412.11420v2 Announce Type: replace Abstract: Estimating the 6D pose and 3D size of an object from visual data is a fundamental task in computer vision. Although single-view geometry is a deeply
arXiv:2609.18167v1 Announce Type: cross Abstract: Adapting to changes in robot dynamics requires learning from new data without discarding experience that may still be useful. In continual model-based
arXiv:2609.18038v1 Announce Type: new Abstract: The world population is growing rapidly, and technology is improving in parallel. Meeting the huge demand for food for these 7 billion people not only d
arXiv:2609.19004v1 Announce Type: cross Abstract: Code optimization plays a crucial role in the development of virtual machine compilers, with optimization frameworks significantly enhancing the perfo
arXiv:2609.17708v1 Announce Type: cross Abstract: Reliable confidence estimation is increasingly central to the trustworthy deployment of language models: a calibrated estimate of the probability that
arXiv:2609.17983v1 Announce Type: new Abstract: KV-cache reuse can reduce inference cost in retrieval-augmented generation and agentic systems, but cached contexts may become stale when retrieved know
arXiv:2602.01898v2 Announce Type: replace Abstract: In many experimental settings, active learning can improve sample efficiency by sequentially selecting where to measure, which is particularly valua
arXiv:2609.18041v1 Announce Type: cross Abstract: Multi-encoder fusion extends Large Audio-Language Models (LALMs) beyond speech-centric recognition, but selecting encoders via intuition or exhaustive
arXiv:2603.26339v2 Announce Type: replace Abstract: We propose an Expected Free Energy-based acquisition function for Bayesian optimization to solve the joint learning and optimization problem, i.e.,
arXiv:2609.17535v1 Announce Type: new Abstract: Language generation research increasingly spans three paradigms: autoregressive decoding, discrete masked diffusion, and continuous flow-matching. Compa
arXiv:2609.18374v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models attach an action module to a Vision-Language Model (VLM) with billions of parameters and pay for that backbone at ev
deepseek v4.1 flash on together ai is leading on ttft for pre-warmed queries for agent workflows, that startup time shows up again on every model turn, so shaving it down matters more as the loop gets
arXiv:2609.18417v1 Announce Type: new Abstract: Multi-turn agent trajectories often contain redundant rounds (failed tool calls, parallel sub-queries, verification-only steps) that inflate both traini
arXiv:2609.18395v1 Announce Type: new Abstract: Policies for robotic manipulation are produced by training on large teleoperated datasets. These datasets typically consist of free-space trajectories,
arXiv:2609.18461v1 Announce Type: new Abstract: Personalized agents are required to reason over long-term history interactions to infer both explicit preferences and implicit behavioral evidence. Whil
arXiv:2609.18773v1 Announce Type: new Abstract: Long-range infrared imaging frequently confronts dense target clusters whose diffraction-limited signatures merge into a single indistinguishable blob,
arXiv:2609.18392v1 Announce Type: new Abstract: Vision-language-action models (VLAs) have trans- formed the field of robotic manipulation in recent years by combining the semantic understanding of LLM
arXiv:2412.16555v4 Announce Type: replace Abstract: Large language models (LLMs) are widely applied in various fields of society due to their powerful reasoning, understanding, and generation capabili
arXiv:2609.18943v1 Announce Type: cross Abstract: Reducing radiation dose in computed tomography significantly degrades image quality and poses challenges for accurate and clinically reliable reconstr
arXiv:2609.18444v1 Announce Type: new Abstract: Weakly supervised class-incremental semantic segmentation (WILSS) aims to train a segmentation model over multiple steps, each introducing new concepts
arXiv:2609.19080v1 Announce Type: new Abstract: As robot capabilities increase, quadratic programming (QP)-based controllers must account for a similarly increasing number of constraints to ensure saf
arXiv:2609.19099v1 Announce Type: new Abstract: Self-emulsifying drug delivery systems (SEDDS) can improve the oral bioavailability of poorly soluble drugs, but identifying high-performing formulation
arXiv:2609.18256v1 Announce Type: new Abstract: Reliability under sparse and heterogeneous failures remains a fundamental challenge for medical image segmentation. High average accuracy can conceal a
arXiv:2609.17913v1 Announce Type: new Abstract: Face--voice association models may rely on language or gender cues in the voice rather than on speaker-specific voice characteristics, which can lead to
arXiv:2609.17534v1 Announce Type: new Abstract: Social desirability and impression management are pervasive sources of response distortion in human personality assessment, yet their effects on Large L
arXiv:2609.18471v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) exhibit strong problem-solving abilities, yet their safety alignment often degrades when handling harmful queries. Existin
arXiv:2609.18623v1 Announce Type: cross Abstract: State-of-the-art vision-language-action models (VLA) for autonomous driving face critical limitations: excessive parameter counts, inefficient high-re
arXiv:2609.18107v1 Announce Type: new Abstract: Graph anomaly detection aims to identify graph structures (e.g., nodes, edges, or subgraphs) that deviate significantly from expected patterns, which su
arXiv:2609.18766v1 Announce Type: cross Abstract: Large audio-language models have shown promise for anti-fraud detection by directly processing speech and reasoning over fraud-related evidence. Their
arXiv:2512.22143v2 Announce Type: replace-cross Abstract: Existing Wi-Fi sensing systems rely on injecting high-rate probing packets to extract channel state information (CSI), leading to communicatio
arXiv:2609.17740v1 Announce Type: new Abstract: Face swapping and face compositing pipelines routinely produce a face that is geometrically well aligned but photometrically implausible: the donor face
arXiv:2609.17695v1 Announce Type: new Abstract: A large language model (LLM) agent can follow more graph paths without acquiring more independent evidence. GraphEcho tests whether agents mistake these
arXiv:2609.18358v1 Announce Type: new Abstract: Robot manipulation policies often struggle to generalize beyond their demonstrations, even when new instructions involve familiar objects and behaviors.
arXiv:2609.18916v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) language models suffer from large parameter counts, which create a significant memory bottleneck. Expert pruning is the most
arXiv:2609.18419v1 Announce Type: cross Abstract: Latent neural operators improve the efficiency of operator learning for partial differential equations (PDEs) by performing the main computation on co
Editor's note: Lucius AI, a tender-intelligence startup covering markets across five continents, runs its entire data platform on AlloyDB for PostgreSQL with a single operator. By migrating semantic s
Important paper on improving agent coordination. On normal tasks, this work shows agents caused harm 0 to 5% of the time. After receiving an unsafe trajectory from another agent, that rose to 40 to 95
arXiv:2609.18504v1 Announce Type: new Abstract: Grasp synthesis aims to generate stable and physically plausible hand--object interactions, and has become a fundamental problem in both human hand mode
arXiv:2609.18825v1 Announce Type: new Abstract: Background: Molecular testing for NPM1 and FLT3-ITD mutations guides critical early treatment decisions in acute myeloid leukemia (AML), but results can
arXiv:2609.17546v1 Announce Type: new Abstract: In this position paper, we argue that legal LLMs' hallucinations should be evaluated as a failure of legal warrant rather than as factual inaccuracy or
arXiv:2609.17842v1 Announce Type: cross Abstract: Conversational visual analytics (CVA) agents powered by large language models generate visualizations and natural-language explanations from open-ende
arXiv:2609.19062v1 Announce Type: new Abstract: Automatic sleep staging is fundamental to personal health monitoring, yet many existing approaches are ill-suited for real-world applications. Tradition
arXiv:2609.17930v1 Announce Type: new Abstract: As AI agents take on long, autonomous tasks, we increasingly oversee rather than perform the work, yet we still judge them almost entirely by whether th
arXiv:2609.19041v1 Announce Type: new Abstract: Informative terrain perception is important for robust reinforcement learning policies in humanoid locomotion. Still, common sensors such as depth camer
arXiv:2609.19039v1 Announce Type: cross Abstract: We introduce the Long-Short-Range Neural Network (LSR-Net), a novel neural operator architecture designed for data-driven forward evolution modeling,
arXiv:2609.18284v1 Announce Type: new Abstract: In recent years, three initiatives have emerged to develop generative language models in Hungary. The motivation behind them is the same. For Hungarian,
arXiv:2609.18088v1 Announce Type: cross Abstract: Detection-free methods for image-to-point cloud registration are prone to erroneous correspondences caused by domain and modality discrepancies, limit
arXiv:2502.14254v3 Announce Type: replace-cross Abstract: Recent advancements in Large Language Models (LLMs) and Vision-Language Models (VLMs) have made them powerful tools in embodied navigation, en
arXiv:2507.21828v2 Announce Type: replace Abstract: While the task of assessing the plausibility of events such as 'news is relevant' has been addressed by a growing body of work, less attention has b