Knowledge catalogue
arXiv:2503.02368v4 Announce Type: replace-cross Abstract: While guided decoding, especially value-guided methods, has emerged as a cost-effective alternative for controlling language model outputs wit
arXiv:2607.02854v1 Announce Type: cross Abstract: Before fixing an issue, it is useful to first reproduce it by generating a bug reproduction test (BRT). However, generating a BRT is itself a challeng
arXiv:2512.22240v5 Announce Type: replace-cross Abstract: Machine learning models are primarily judged by predictive performance, especially in applied genomics, where explanations are read as biologi
Excellent investigation of the mechanics of language models. 🫢A notable blindspot, however: several teams have actually been **directly** comparing the working of LLMs to those of the human brain 🧠 fo
arXiv:2607.03146v1 Announce Type: new Abstract: Vision-language-action (VLA) models open a new path toward intuitive robot control by directly linking perception, language, and action in a single end-
Google expands Managed Agents in Gemini API with support for background execution , and adds the ability to register remote Model Context Protocol (MCP) servers to extend agent capabilities . Develope
arXiv:2607.04010v1 Announce Type: new Abstract: Bangladesh has an estimated 1.17 mental-health professionals per 100,000 population and only six child psychiatrists nationwide. No Bengali-language, cu
arXiv:2503.10496v2 Announce Type: replace-cross Abstract: Modeling natural phenomena with artificial neural networks (ANNs) often provides highly accurate predictions. However, ANNs often suffer from
arXiv:2606.16302v2 Announce Type: replace Abstract: Rapid and accurate flood prediction is essential for disaster response and mitigation planning. Synthetic Aperture Radar (SAR) sensors in satellites
arXiv:2607.04548v1 Announce Type: cross Abstract: Novel category discovery aims to identify unseen classes from unlabeled data by transferring knowledge from labeled categories, but most existing meth
arXiv:2607.03703v1 Announce Type: new Abstract: Reinforcement Learning (RL) has emerged as a powerful paradigm for adaptive traffic signal control. However, in safety-critical infrastructure like traf
arXiv:2601.21523v2 Announce Type: replace Abstract: To promote cooperation in Multi-Agent Reinforcement Learning, the reward signals of all agents can be aggregated together, forming global rewards th
arXiv:2504.17331v3 Announce Type: replace-cross Abstract: Locomotion plays a crucial role in shaping the user experience within virtual reality environments. In particular, hands-free locomotion offer
arXiv:2607.04190v1 Announce Type: new Abstract: Global reanalysis products such as ERA5-Land provide spatially complete weather fields but at resolutions too coarse for local applications, particularl
arXiv:2607.03754v1 Announce Type: new Abstract: Unmanned aerial vehicle (UAV) target segmentation remains challenging due to the small size of objects, appearance variations, cluttered backgrounds, an
arXiv:2511.19636v2 Announce Type: replace-cross Abstract: In many machine learning problems, there may exist multiple models that achieve nearly identical predictive performance while relying on funda
arXiv:2607.03110v1 Announce Type: new Abstract: Multi-Exposure Fusion (MEF) effectively extends dynamic range, but practical deployment is hindered by motion-induced ghosting and the scarcity of high-
arXiv:2508.04928v5 Announce Type: replace-cross Abstract: We propose a method to extend foundational monocular depth estimators (FMDEs), trained on perspective images, to fisheye images. Despite being
arXiv:2508.16771v3 Announce Type: replace-cross Abstract: Code Language Models (CodeLLMs) learn token importance from data correlations, whereas human developers attend selectively to semantically sal
arXiv:2607.04698v1 Announce Type: new Abstract: The rapid proliferation of Internet of things (IoT) devices has significantly expanded the cyber-attack surface, necessitating robust and privacy-preser
Fable 5's event period was extended to July 12th, likely due to unexpectedly high upgrade rates to Claude Max in the preceding days. This announcement suggests strong user interest in Anthropic's prem
Chinese AI startup DeepSeek is developing its own inference chips to reduce Nvidia dependence and break U.S. export controls, as China moves to protect its AI ecosystem. DeepSeek has been quietly deve
arXiv:2607.04523v1 Announce Type: cross Abstract: Generic statements like 'tigers are striped' and 'cars have radios' communicate information that is, in general, true. However, while the first statem
arXiv:2509.15206v3 Announce Type: replace Abstract: The high memory demands of generative language models have drawn attention to quantization, which reduces memory usage by mapping model weights to l
arXiv:2607.03180v1 Announce Type: new Abstract: Multimodal diffusion transformers (MM-DiTs) have emerged as the prevalent backbone for modern text-to-image generation systems. However, they exhibit cr
arXiv:2607.05355v1 Announce Type: new Abstract: Attribution scores increasingly identify which neuron rows of a language model matter for applications such as pruning, interpretability, and editing fo
SpaceX's Falcon 9 rocket successfully completed a landing, likely referring to either a first-stage booster landing on a drone ship or ground pad, or a full rocket recovery. Elon Musk announced the co
SpaceX's Falcon rocket successfully deployed 81 satellites into orbit in a single launch, demonstrating the vehicle's significant payload capacity. This mission likely involved Starlink satellites or
arXiv:2607.03209v1 Announce Type: new Abstract: This paper introduces a fast method for high-quality 3D Gaussian Splatting (3DGS) reconstruction without traditional Structure-from-Motion (SfM). The pr
arXiv:2607.05095v1 Announce Type: new Abstract: Temporal Graph Neural Networks (TGNNs) are widely used for learning from dynamic graphs in applications such as recommendation, social network analysis,
arXiv:2607.03987v1 Announce Type: new Abstract: Sampling-based motion planners have been shown to be effective for systems with complex kinodynamic constraints and high dimensionality. However, these
arXiv:2607.04062v1 Announce Type: cross Abstract: We study the fundamental classification problem of computing a separating hyperplane for a binary-labeled dataset of size n with normalized d-dimensio
arXiv:2508.02641v2 Announce Type: replace-cross Abstract: Molecular crystal structure prediction (CSP) is essential for applications in pharmaceuticals and organic electronics. However, CSP remains ch
arXiv:2607.03822v1 Announce Type: new Abstract: Vision-based 3D occupancy prediction fundamentally relies on the 2D-to-3D view transformation. Current paradigms predominantly utilize explicit physical
arXiv:2511.06454v3 Announce Type: replace-cross Abstract: We analyze an algorithm for assigning weights prior to scalarization in discrete multi-objective problems arising from data analysis. The algo
arXiv:2607.03763v1 Announce Type: cross Abstract: Federated Transformer training increasingly relies on local AdamW, whose adaptive updates can provide much stronger local progress than SGD-based trai
arXiv:2607.03334v1 Announce Type: cross Abstract: The federated learning (FL) paradigm fosters distributed pervasive computing combined with artificial intelligence techniques, allowing for optimized
arXiv:2607.02636v1 Announce Type: cross Abstract: Object detection is a fundamental capability for AI-driven perception in safety-critical drone and edge-vision systems, including disaster response, o
arXiv:2607.04170v1 Announce Type: new Abstract: Federated Learning (FL) enables decentralized training without data sharing, but suffers from statistical heterogeneity across clients, leading to clien
arXiv:2607.04158v1 Announce Type: cross Abstract: Federated learning (FL) is severely hindered by statistical heterogeneity due to variations in scanners, acquisition protocols, and patient population
arXiv:2607.04085v1 Announce Type: cross Abstract: Routing-prediction federated learning has emerged as a new paradigm that reframes inter-client heterogeneity as a resource for system-level intelligen
arXiv:2607.03387v1 Announce Type: new Abstract: Tactile perception is indispensable for contact-rich manipulation, yet integrating it into Vision-Language-Action (VLA) models often induces modality co
arXiv:2510.15686v2 Announce Type: replace Abstract: Learning coordinated behaviors for multi-robot systems from only a few demonstrations is difficult because temporal task dependencies and spatial tr
arXiv:2607.04563v1 Announce Type: new Abstract: As language modeling technology matures, there is an increasing research focus on the composition and curation of datasets used to train these models. F
arXiv:2607.04449v1 Announce Type: new Abstract: Field-boundary maps support crop monitoring, irrigation planning, and yield estimation, but many smallholder parcels span only a few 10 m Sentinel-2 pix
arXiv:2607.02630v1 Announce Type: cross Abstract: Hardware accelerators now sit on the critical path of online serving. GPUs, FPGAs, and increasingly remote services such as hardware security modules,
arXiv:2607.04019v1 Announce Type: cross Abstract: Physical sensing and actuation noise floors should inform how much belief resolution a decision-making system can reliably use. We introduce Finite Re
arXiv:2607.04006v1 Announce Type: cross Abstract: We establish finite-sample closed-loop stability guarantees for Model Predictive Path Integral (MPPI) control applied to discrete-time Linear Time-Inv
arXiv:2607.05375v1 Announce Type: cross Abstract: Occupancy ratios correct distribution shift in offline reinforcement learning and are central to off-policy evaluation. Existing primal-dual and minim
arXiv:2607.04315v1 Announce Type: cross Abstract: This paper studies the problem of identifying the treatment that maximizes the expected natural direct potential outcome (NDPO), which captures the po
arXiv:2607.04461v1 Announce Type: new Abstract: Inference-time scaling for text-to-image generation has progressed from simple Best-of-N (BoN) sampling to guided search methods that verify and steer c
arXiv:2504.07337v2 Announce Type: replace Abstract: Aggregating temporal signals from historic interactions is a key step in future link prediction on dynamic graphs. However, incorporating long histo
arXiv:2602.05305v3 Announce Type: replace-cross Abstract: Generating long-form content, such as minute-long videos and extended texts, is increasingly important for modern generative models. Block dif
arXiv:2607.05201v1 Announce Type: new Abstract: In non-stationary streaming environments, simultaneously adapting to complex, non-linear domain shifts via continual learning while mitigating the catas
arXiv:2607.03509v1 Announce Type: new Abstract: Recent progress in large-scale generative models has substantially advanced video generation, yet existing methods remain constrained by a rigid inferen
arXiv:2607.04260v1 Announce Type: new Abstract: Aerial physical interaction represents a promising direction for next-generation unmanned aerial vehicles (UAVs), but it requires an aerial platform tha
arXiv:2512.21196v2 Announce Type: replace Abstract: Collective motion inspired by animal groups offers powerful design principles for autonomous aerial swarms. We present a bio-inspired 3D flocking al
arXiv:2607.03100v1 Announce Type: cross Abstract: Modern web applications increasingly expose accessibility barriers through interaction flows rather than static page snapshots. Keyboard traps, focus
While large language models (LLMs) and coding agents are often applied to user interface (UI) development, developers find it difficult to reliably assess their proficiency in visual and interaction d
arXiv:2607.05261v1 Announce Type: new Abstract: We present FlowMark, a video watermarking framework guided by automatically predicted object masks. In contrast to prior region-based approaches that re