Knowledge catalogue
arXiv:2605.15649v1 Announce Type: new Abstract: Developing effective surrogates (performance predictors) for Neural Architecture Search (NAS) typically requires expensive fine-tuning or the engineerin
arXiv:2602.08324v3 Announce Type: replace Abstract: Chain-of-Thought (CoT) reasoning successfully enhances the reasoning capabilities of Large Language Models (LLMs), yet it incurs substantial computa
arXiv:2605.16085v1 Announce Type: cross Abstract: Relational databases store much of the world's structured information, and they are essential for driving complex predictive applications. However, de
arXiv:2605.15913v1 Announce Type: cross Abstract: Block attention, which processes the input as separate blocks that cannot attend to one another, offers significant potential to improve KV cache reus
arXiv:2605.16087v1 Announce Type: cross Abstract: Deep Neural Networks have become the dominant solution for Autonomous Driving perception, but their opacity conflicts with emerging Trustworthy AI gui
arXiv:2605.15257v1 Announce Type: new Abstract: Chain-of-thought (CoT) monitoring is one of the most promising tools we have for detecting model misbehavior, but its effectiveness depends on models fa
arXiv:2412.12636v3 Announce Type: replace-cross Abstract: Large-scale ML training jobs are frequently interrupted by hardware and software anomalies, failures, and management events. Existing solution
arXiv:2510.10454v2 Announce Type: replace Abstract: Large language models (LLMs) offer a generalizable approach for modeling patient trajectories, but suffer from the long and noisy nature of electron
arXiv:2605.15608v1 Announce Type: new Abstract: Decoder-only transformers compute the conditional probability of the next token from a sequence of past observations. This paper derives, from first pri
arXiv:2605.15413v1 Announce Type: new Abstract: Despite the remarkable success of transformer architectures in natural language processing, their scalability limitations remain poorly understood throu
arXiv:2510.19315v3 Announce Type: replace-cross Abstract: We study succinctness as a measure of the expressive power of transformers. Succinctness -- how compactly a formalism can describe a language
arXiv:2602.05414v2 Announce Type: replace Abstract: Global warming has intensified the frequency and severity of extreme weather events, which degrade CCTV signal and video quality while disrupting tr
arXiv:2412.06853v4 Announce Type: replace-cross Abstract: This paper proposes a novel loss function, called 'Tube Loss', for simultaneous estimation of bounds of a Prediction Interval (PI) in the regr
arXiv:2605.15533v1 Announce Type: cross Abstract: Video editing poses a significant challenge. While a series of tuning-free methods circumvent the need for extensive data collection and model trainin
arXiv:2605.15579v1 Announce Type: cross Abstract: To fit diverse display and bandwidth constraints, high-frame-rate videos are temporally downscaled to low-frame-rate (LFR) and later upscaled, requiri
arXiv:2512.01537v2 Announce Type: replace-cross Abstract: Recent neural audio codecs have achieved impressive reconstruction quality, typically relying on quantization methods such as Residual Vector
arXiv:2605.15421v1 Announce Type: new Abstract: In this study, we explore in depth a few under-studied topics at the intersection of uncertainty estimation and segmentation. Prior work has shown that
arXiv:2605.15735v1 Announce Type: cross Abstract: Vision--language--action (VLA) models are typically built by fine-tuning a pretrained vision--language model (VLM) on action data. However, we show th
arXiv:2605.15894v1 Announce Type: cross Abstract: Rapid and accurate wildfire smoke severity assessment from satellite images is essential for emergency response, air quality modeling, and human healt
arXiv:2605.15388v1 Announce Type: new Abstract: Stochastic estimators are fundamental to large-scale optimization, where population quantities must be inferred from noisy oracle observations. Although
arXiv:2605.15305v1 Announce Type: cross Abstract: A unified simulator that can model diverse physical phenomena without solver-specific redesign is a long-standing goal across simulation science. We p
arXiv:2510.03161v2 Announce Type: replace-cross Abstract: With the rapid advancements in image generation, synthetic images have become increasingly realistic, posing significant societal risks, such
arXiv:2605.15285v1 Announce Type: cross Abstract: Derivative-Informed Operator Learning (DIOL), i.e. learning a (nonlinear) operator and its derivatives, is an open research frontier at the foundation
arXiv:2605.16230v1 Announce Type: cross Abstract: Magnetic order is a fundamental property of materials, governing collective behavior and enabling a broad range of functionalities. Yet magnetic struc
arXiv:2601.21028v2 Announce Type: replace-cross Abstract: AI-generated media is radically changing the way content is both consumed and produced on the internet, and in no place is this potentially mo
arXiv:2605.15876v1 Announce Type: new Abstract: Vision-Language Models (VLMs) excel at 2D tasks such as grounding and captioning, yet remain limited in 3D understanding. A key limitation is their text
arXiv:2605.15583v1 Announce Type: new Abstract: We propose a method of estimating a 3D human pose from a single view without 3D supervision. The key to our method is to leverage the 2D diffusion prior
arXiv:2605.15920v1 Announce Type: cross Abstract: We developed a tool for detecting domain shifts, namely subtle differences in the probability distributions of datasets. We identify these shifts usin
arXiv:2505.11708v3 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) agents are increasingly used to simulate sophisticated cyberattacks, but their decision-making processes remain op
arXiv:2605.15661v1 Announce Type: cross Abstract: Classifier-free guidance (CFG) is the primary control over how strongly text semantics move a flow-based sampler, yet standard practice holds its scal
arXiv:2605.16020v1 Announce Type: new Abstract: Monte Carlo methods are essential across diverse scientific fields, yet their efficiency is frequently hampered by critical slowing down-a sharp increas
arXiv:2605.15677v1 Announce Type: new Abstract: Despite the rapid advancements in Vision-Language Models (VLMs), a critical gap remains in their ability to handle structured, controllable diagrammatic
arXiv:2511.03606v2 Announce Type: replace-cross Abstract: The study of self-normalized processes plays a crucial role in a wide range of applications, from sequential decision-making to econometrics.
arXiv:2605.15228v1 Announce Type: new Abstract: Modern cloud and enterprise systems rely on identity-centric authorization, assuming that callers possessing valid credentials are safe to execute comma
arXiv:2508.03810v4 Announce Type: replace-cross Abstract: Neural Network (NN) architectures that break statistical independence of parameters have been proposed as a new approach for simulating local
arXiv:2605.15458v1 Announce Type: new Abstract: Video diffusion models have made rapid progress in perceptual realism and temporal coherence, but they remain primarily optimized for plausible generati
arXiv:2505.18134v3 Announce Type: replace Abstract: Vision-language models (VLMs) have achieved strong results on coding and math benchmarks that are challenging for humans, yet their ability to perfo
arXiv:2605.16079v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have shown significant progress in video understanding, yet they face substantial challenges in tasks requiring p
arXiv:2510.08398v4 Announce Type: replace Abstract: The recent rapid advancement of Text-to-Video (T2V) generation technologies are engaging the trained models with more world model ability, making th
arXiv:2504.05451v2 Announce Type: replace Abstract: Traditional methods for view-invariant learning rely on controlled multi-view training data with minimal scene clutter. However, they struggle with
arXiv:2504.21850v3 Announce Type: replace Abstract: Visual instruction tuning (VIT) datasets have grown rapidly in scale, yet the informativeness of individual training samples has largely been overlo
arXiv:2605.15672v1 Announce Type: cross Abstract: Vision-language models (VLMs) achieve strong performance on multimodal benchmarks, but may still lack robust control over basic visual operations. We
arXiv:2605.15604v1 Announce Type: cross Abstract: Modern language models often need to optimize a primary accuracy objective while also accommodating secondary behavioral preferences, such as verbosit
arXiv:2605.16127v1 Announce Type: new Abstract: While multi-modal 3D semantic occupancy prediction typically enhances robustness by fusing camera and LiDAR inputs, its effectiveness is fundamentally c
arXiv:2511.14282v2 Announce Type: replace-cross Abstract: Deep neural networks achieve outstanding performance across vision and language tasks, yet their large parameter counts limit deployment in re
arXiv:2512.00778v2 Announce Type: replace Abstract: Preference optimization (PO) is indispensable for large language models (LLMs), with methods such as direct preference optimization (DPO) and proxim
arXiv:2602.04003v3 Announce Type: replace Abstract: Most adversarial threats in artificial intelligence (AI) target the computational behavior of models rather than the humans who rely on them. Yet mo
arXiv:2605.15959v1 Announce Type: cross Abstract: Physics-informed neural networks (PINNs) are powerful surrogates for differential equations but are notoriously difficult to train due to spectral bia
arXiv:2605.15484v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) networks promise favorable accuracy-compute trade-offs, yet practical vision deployments are hindered by expert collapse and li
arXiv:2510.06062v2 Announce Type: replace Abstract: Reinforcement learning (RL) has shown great promise in large language models (LLMs) post-training, which typically rely on token-level clipping to m
arXiv:2605.15557v1 Announce Type: new Abstract: Continuous diffusion and flow models are attractive for non-autoregressive text generation because they can update all positions in parallel. A major di
arXiv:2605.15430v1 Announce Type: cross Abstract: This study demonstrates a method to locate an ideal perch location on a tree for vision-guided autonomous tree-perching drones. Various image processi
arXiv:2605.16035v1 Announce Type: cross Abstract: AI agents are increasingly deployed to act autonomously in the world, yet there is still no reliable way to trace a harmful agent back to the account
arXiv:2511.02342v3 Announce Type: replace Abstract: Aerial manipulation combines the maneuverability of multirotors with the dexterity of robotic arms to perform complex tasks in cluttered spaces. Yet
arXiv:2605.15440v1 Announce Type: new Abstract: Surprisal theory posits that the processing difficulty of a word is determined by its predictability in context, offering a potential link between human
arXiv:2605.15619v1 Announce Type: new Abstract: Gliding offers small fixed-wing UAVs extended endurance and silent operation but requires accurate energy management, especially under wind disturbances
arXiv:2605.15843v1 Announce Type: new Abstract: Recent 3D world modeling systems based on generative scene synthesis, such as Marble, can create coherent and explorable 3D environments, yet their outp
arXiv:2605.15964v1 Announce Type: cross Abstract: Aerial vision-language navigation (VLN) requires agents to follow natural-language instructions through closed-loop perception and action in 3D enviro
arXiv:2605.15505v1 Announce Type: new Abstract: In enterprise operations, the context required for an AI agent task is scattered across systems of record, static information stores, and communication
arXiv:2605.16046v1 Announce Type: cross Abstract: Semantic code search has been widely adopted in both academia and industry. These approaches embed natural-language queries and code snippets into a s