Knowledge catalogue
arXiv:2604.26250v1 Announce Type: new Abstract: While Vision-Language Models (VLMs) have achieved state-of-the-art performance in general visual tasks, their perceptual robustness remains remarkably b
arXiv:2604.26209v1 Announce Type: cross Abstract: Some text generation tasks, such as Attribute Value Extraction (AVE), require decoding multiple independent sequences from the same document context.
arXiv:2604.26281v1 Announce Type: cross Abstract: To preserve or not to preserve prosody is a central question in voice anonymization. Prosody conveys meaning and affect, yet is tightly coupled with s
arXiv:2604.26173v1 Announce Type: cross Abstract: An effective way to scale up test-time compute of large language models is to sample multiple responses and then select the best one, as in Grok Heavy
arXiv:2510.06735v2 Announce Type: replace Abstract: Bayesian causal discovery benefits from prior information elicited from domain experts, and in heterogeneous domains any prior knowledge would be ba
arXiv:2604.26673v1 Announce Type: cross Abstract: Uncertainty estimation is essential for robust decision-making in the presence of ambiguous or out-of-distribution inputs. Gaussian Processes (GPs) ar
arXiv:2603.01999v2 Announce Type: replace-cross Abstract: Reliable obstacle avoidance in industrial settings demands 3D scene understanding, but widely used 2D LiDAR sensors perceive only a single hor
arXiv:2507.01449v3 Announce Type: replace Abstract: Speculative decoding (SD), where a small draft model is employed to propose draft tokens in advance and then the target model validates them in para
arXiv:2604.26508v1 Announce Type: cross Abstract: Deploying Vision-Language Models (VLMs) on edge devices remains challenging due to their substantial computational and memory demands, which exceed th
arXiv:2604.26221v1 Announce Type: cross Abstract: Open-vocabulary semantic segmentation (OVSS) in remote sensing images is a promising task that employs textual descriptions for identifying undefined
arXiv:2604.26694v1 Announce Type: cross Abstract: We propose X-WAM, a Unified 4D World Model that unifies real-time robotic action execution and high-fidelity 4D world synthesis (video + 3D reconstruc
// When to Retrieve During Reasoning // Pay attention to this one, AI devs. (bookmark it) Most RAG systems retrieve once, before the model starts reasoning. Large reasoning models like o1 and R1 don't
Recent advances in large language models (LLMs) test-time computing have introduced the capability to perform intermediate chain-of-thought (CoT) reasoning (thinking) before generating answers. While
arXiv:2411.05174v2 Announce Type: replace Abstract: We consider the problem of estimating the transition dynamics T^* from near-optimal expert trajectories in the context of offline model-based reinfo
arXiv:2603.26783v2 Announce Type: replace Abstract: Diffusion models can be challenged in the low signal-to-noise regime, where they have to make pixel-level predictions despite the presence of high n
arXiv:2602.01785v2 Announce Type: replace Abstract: Large Language Models (LLMs) have achieved remarkable success in source code understanding, yet as software systems grow in scale, computational eff
arXiv:2603.20645v2 Announce Type: replace Abstract: Diffusion models have become a leading framework in generative modeling, yet their theoretical understanding -- especially for high-dimensional data
arXiv:2604.24997v1 Announce Type: new Abstract: Open-vocabulary semantic segmentation requires assigning pixel-level semantic labels while supporting an open and unrestricted set of categories. Traini
arXiv:2604.25372v1 Announce Type: cross Abstract: While it is generally understood that zeroth-order (ZO) algorithms have an extra dependency on their number of iterations for any choice of parameters
arXiv:2603.01070v2 Announce Type: replace Abstract: Solving complex geometric problems inherently requires interleaved reasoning: a tight alternation between constructing diagrams and performing logic
arXiv:2604.25858v1 Announce Type: new Abstract: Transformers have demonstrated a strong ability for in-context learning (ICL), enabling models to solve previously unseen tasks using only example input
arXiv:2604.25062v1 Announce Type: cross Abstract: Cellular differentiation is governed by gene regulatory networks, the high-dimensional stochastic biochemical systems that determine the transcription
arXiv:2604.25405v1 Announce Type: new Abstract: Camera-based 3D object detection and tracking are central to autonomous driving, yet precise 3D object localization remains fundamentally constrained by
arXiv:2604.25178v1 Announce Type: new Abstract: Achieving a desirable balance between rendering quality and real-time performance is a long-standing challenge in modern game and rendering engines, par
arXiv:2604.25200v1 Announce Type: cross Abstract: Public agencies are beginning to consider large language models (LLMs) as decision-support tools for grant evaluation. This creates a practical govern
arXiv:2604.25578v1 Announce Type: new Abstract: We present Marco-MoE, a suite of fully open multilingual sparse Mixture-of-Experts (MoE) models. Marco-MoE features a highly sparse design in which only
arXiv:2603.15954v2 Announce Type: replace Abstract: Real-time AI experiences call for on-device large language models (OD-LLMs) optimized for efficient deployment on resource-constrained hardware. The
arXiv:2412.07584v2 Announce Type: replace Abstract: Current video retrieval systems, especially those used in competitions, primarily focus on querying individual keyframes or images rather than encod
arXiv:2604.25819v1 Announce Type: new Abstract: In this work, we propose Mutual Forcing, a framework for fast autoregressive audio-video generation with long-horizon audio-video synchronization. Our a
arXiv:2604.25028v1 Announce Type: new Abstract: Recent work revisiting measurability in the fundamental theorem of statistical learning imposes Borel measurability of ghost-gap suprema. We show that,
arXiv:2604.25306v1 Announce Type: new Abstract: FlashAttention improves efficiency through tiling, but its online softmax still relies on floating-point arithmetic for numerical stability, making full
Qwen3.6 27B is a 27-billion parameter language model that can achieve approximately 60 tokens per second throughput when running on dual RTX 5060 Ti GPUs with 16GB memory each, using the vLLM inferenc
arXiv:2604.05594v2 Announce Type: replace Abstract: Pixel-level annotation is costly in low-resource dermoscopy. We present RABC-Net, a reliability-aware annotation-free segmentation system that combi
arXiv:2604.25889v1 Announce Type: new Abstract: Current deepfake detection models achieve state-of-the-art performance on pristine academic datasets but suffer severe spatial attention drift under rea
arXiv:2603.17729v3 Announce Type: replace Abstract: Recent advances in Large Vision-Language Models (LVLMs) have enabled training-free Fine-Grained Visual Recognition (FGVR). However, effectively expl
arXiv:2604.25367v1 Announce Type: new Abstract: In this paper, we present Self-DACE++, an improved unsupervised and lightweight framework for Low-Light Image Enhancement (LLIE), building upon our prev
The momentum is undeniable: the world’s fastest-growing AI startups are building with Google Cloud. Instead of stitching together fragmented point solutions, founders are building their businesses her
arXiv:2604.25150v1 Announce Type: new Abstract: Overparameterization is central to the success of deep learning, yet the mechanisms by which it improves optimization remain incompletely understood. We
arXiv:2604.25316v1 Announce Type: new Abstract: Domain adaptation (DA) addresses the challenge of transferring a machine learning model trained on a source domain to a target domain with a different d
arXiv:2604.24172v1 Announce Type: cross Abstract: This paper uses a minimum divergence framework to introduce a new way of calculating model weights that can be used to average probabilistic predictio
A few notes on how to get started with building LLM Knowledge Bases. @karpathy popularized it but most people don't know where to start. Everyone should be creating LLM Wikis. Live session tomorrow. S
arXiv:2602.15853v2 Announce Type: replace-cross Abstract: We propose a lightweight explainable guardrail (LEG) method to detect unsafe prompts. LEG uses a multi-task learning architecture to jointly l
arXiv:2510.15479v2 Announce Type: replace Abstract: We study counterfactual prediction under assignment bias and propose a mathematically grounded, information-theoretic approach that removes treatmen
arXiv:2505.01595v2 Announce Type: replace-cross Abstract: We present a state-of-the-art model for fine-grained probability estimation of propositions conditioned on context. Recent advances in large l
arXiv:2601.06166v2 Announce Type: replace Abstract: Accelerated dynamic volumetric magnetic resonance imaging (4DMRI) is essential for applications relying on motion resolution. Existing 4DMRI produce
arXiv:2601.22925v2 Announce Type: replace-cross Abstract: Recent years have seen a rapid surge in research leveraging Large Language Models (LLMs) for recommendation. These methods typically employ su
arXiv:2604.24018v1 Announce Type: new Abstract: This paper studies the problem of robot performance evaluation, focusing on how to obtain accurate and efficient estimates of real-world behavior under
arXiv:2604.24273v1 Announce Type: new Abstract: The deployment of intelligent reinforcement learning (RL) agents on resource-constrained edge devices remains a fundamental challenge due to the substan
arXiv:2508.08127v2 Announce Type: replace Abstract: The security of LLM-based multi-agent systems (MAS) is critically threatened by propagation vulnerability, where malicious agents can distort collec
arXiv:2604.24136v1 Announce Type: new Abstract: Pretrained diffusion models have revolutionized real-world image super-resolution (Real-ISR) but suffer from computational bottlenecks due to iterative
arXiv:2604.23508v1 Announce Type: new Abstract: Burst image super resolution (BISR) aims to construct a single high-resolution (HR) image by aggregating information from multiple low-resolution (LR) f
arXiv:2604.23876v1 Announce Type: new Abstract: We present Cardiac Stability Theory (CST), an axiomatically grounded framework formally defining cardiovascular health as a stability margin around a ca
arXiv:2604.23022v1 Announce Type: cross Abstract: Two-stage recommender systems first choose a candidate generator and then rank items within the generated set. Because the generator decides which ite
arXiv:2604.24622v1 Announce Type: cross Abstract: Flow-based vision-language-action (VLA) policies offer strong expressivity for action generation, but suffer from a fundamental inefficiency: multi-st
arXiv:2604.05500v2 Announce Type: replace Abstract: Nighttime image dehazing faces a more complex degradation pattern than its daytime counterpart, as haze scattering couples with low illumination, no
arXiv:2604.23003v1 Announce Type: new Abstract: In this paper, we propose a Physics-Informed Neural Network framework for time-dependent simulations of pollution propagation originating from moving em
arXiv:2504.09499v2 Announce Type: replace-cross Abstract: Hattrick is a free web-based probabilistic football manager game with over 200,000 users competing for titles at national and international le
arXiv:2604.24162v1 Announce Type: cross Abstract: Defending against backdoor attacks in large language models remains a critical practical challenge. Existing defenses mitigate these threats but typic
arXiv:2604.23636v1 Announce Type: new Abstract: In this work, we study Source-Free Unsupervised Domain Adaptation under corruption-induced domain shifts, where performance degradation is caused by nat
arXiv:2506.21107v3 Announce Type: replace Abstract: Estimating single-cell responses across various perturbations facilitates the identification of key genes and enhances drug screening, significantly