Knowledge catalogue
arXiv:2608.17071v1 Announce Type: new Abstract: We present KernelArc, a multi-agent framework for autonomous GPU kernel optimization across heterogeneous workloads. Strategy-specialized agents run in
arXiv:2608.17561v1 Announce Type: new Abstract: The health of marine ecosystems is a critical indicator of global environmental change, yet the physical constraints of underwater observation and the i
arXiv:2603.26929v2 Announce Type: replace Abstract: Interactive video segmentation often requires many user interventions for robust performance in challenging scenarios (e.g., occlusions, object sepa
arXiv:2608.17635v1 Announce Type: new Abstract: Vision-LSTM (ViL) enables efficient global modeling, but its cost still scales with the number of spatial tokens, so existing segmenters confine ViL to
arXiv:2608.17178v1 Announce Type: new Abstract: Video self-supervised learning through masked spatiotemporal prediction has emerged as a promising paradigm for learning feature representations from un
arXiv:2502.13428v2 Announce Type: replace-cross Abstract: This work investigates how to improve large language model (LLM)-based reasoning for knowledge base question answering (KBQA) via Monte Carlo
arXiv:2608.17402v1 Announce Type: new Abstract: Vision encoders are a critical component of vision-language models, and scaling their capacity effectively improves performance. However, dense scaling
arXiv:2608.17616v1 Announce Type: new Abstract: We present MoNe, a lightweight modular neural memory that attaches to any frozen pretrained Transformer to enable long-context inference without retrain
arXiv:2506.01297v5 Announce Type: replace Abstract: Representation learning of geospatial locations remains a core challenge in achieving general geospatial intelligence, with increasingly diverging p
arXiv:2608.17328v1 Announce Type: new Abstract: Facial biometric recognition systems currently face compound threats intertwining generative AI and high-fidelity physical spoofing. Existing defenses s
arXiv:2608.17559v1 Announce Type: new Abstract: In this paper, we tackle the problem of performing consistent, unified modifications to a multi-shot video sequence. This task is particularly challengi
arXiv:2608.16966v1 Announce Type: new Abstract: In modern intelligent transportation systems, it is essential to accurately estimate vehicle positions, especially in mixed traffic conditions where bot
arXiv:2608.17605v1 Announce Type: cross Abstract: Conversational AI is moving beyond isolated text prompts toward sustained, multimodal interaction. In real conversations, users clarify goals, revise
arXiv:2508.05778v2 Announce Type: replace Abstract: Nudging is an empirical data assimilation technique that incorporates an observation-driven control term into the model dynamics. The trajectory of
arXiv:2608.17262v1 Announce Type: cross Abstract: This paper considers robust nonadaptive regulation for general nonlinear systems in an output-feedback setting with arbitrarily high relative degree.
arXiv:2608.17162v1 Announce Type: new Abstract: What a language model internalizes from fine-tuning is usually diagnosed after the fact. We make it an experimental variable. OraclePhys is a systematic
arXiv:2608.17289v1 Announce Type: new Abstract: Group-relative policy optimization has emerged as a key paradigm for training agentic large language models (LLMs) on multi-turn interactive tasks. Howe
arXiv:2608.18035v1 Announce Type: new Abstract: Traffic elements such as traffic lights and road signs play a fundamental role in human driving decisions and should naturally influence end-to-end driv
arXiv:2608.17962v1 Announce Type: new Abstract: Recent progress in robotic learning has been fueled by large-scale datasets collected in everyday environments. However, most existing datasets emphasiz
arXiv:2602.13840v2 Announce Type: replace Abstract: Large language model (LLM) agents are increasingly deployed in personalized tasks involving sensitive, context-dependent information, where privacy
arXiv:2608.16913v1 Announce Type: new Abstract: Road safety monitoring has historically been reactive, relying on crash-record analysis after fatalities and injuries have already occurred. Proactive i
arXiv:2608.17129v1 Announce Type: new Abstract: Vision-language Models (VLMs) excel at 2D grounding, spatial reasoning and agentic tool-based planning in static scenes. However, consider asking a home
arXiv:2608.16984v1 Announce Type: cross Abstract: Recent monocular depth estimators achieve strong zero-shot generalization, yet often struggle to preserve fine-grained structures and object boundarie
arXiv:2608.17288v1 Announce Type: new Abstract: GPT attention measures token compatibility through dot-product similarity. This mechanism is simple, effective, and memory-efficient. But it does not ex
arXiv:2608.17163v1 Announce Type: cross Abstract: Off-policy reinforcement learning (RL) has become increasingly sample-efficient, enabling applications such as RL fine-tuning of Vision-Language-Actio
Qwen 27B is really good local model but, when you use it, it is immediately absolutely and obviously nowhere near as good as the other models listed here for agentic tasks, and especially for the kind
I've been working on a depth pruning approach and decided to try it out on the new Qwen3.8-27B model. I managed to get the model down to about 22.7B params without severe reasoning degradation. No fin
arXiv:2608.17414v1 Announce Type: new Abstract: Chart editing requires inferring and modifying visualization code from a reference chart image based on an editing instruction, challenging fine-grained
arXiv:2604.01460v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) have achieved remarkable progress in video understanding. However, seemingly plausible outputs often suffer
arXiv:2608.17347v1 Announce Type: cross Abstract: Repetition is a fundamental mechanism in human learning, where revisiting successful experiences strengthens memory, consolidates skills, and improves
arXiv:2608.17641v2 Announce Type: new Abstract: We present rl-triton, an open-source library of high-performance GPU kernels for reinforcement learning credit assignment, implemented in Triton. The co
arXiv:2608.16965v1 Announce Type: new Abstract: The dominance of majority classes in real-world datasets poses a fundamental challenge to randomized neural networks, often biasing decision boundaries
arXiv:2608.17475v1 Announce Type: new Abstract: Vision foundation models have recently advanced multi-modal salient object detection (MSOD) through parameter-efficient tuning and prompt learning. Howe
arXiv:2608.17553v1 Announce Type: new Abstract: Cameras are ubiquitous sensors in robotics due to their compact form factor and the perceptual richness captured through visual information. Monocular S
arXiv:2608.17314v1 Announce Type: new Abstract: Animatable human avatars are routinely reconstructed from multi-view video under a silent assumption: that every pixel of a frame observes the same inst
arXiv:2507.15455v3 Announce Type: replace-cross Abstract: We propose a mesh-free policy iteration framework that combines classical dynamic programming with physics-informed neural networks (PINNs) to
arXiv:2608.17931v1 Announce Type: new Abstract: Recent advances in AI have revolutionized speech processing, yet effective speech understanding requires discerning not just what is said, but how it is
arXiv:2608.18050v1 Announce Type: new Abstract: AI agents increasingly perform knowledge work (i.e., produce and modify persistent digital artifacts such as code repositories, documents, spreadsheets,
arXiv:2608.17237v1 Announce Type: cross Abstract: Converting structural framing plans into editable finite-element model drafts remains labor-intensive and prone to transcription error. Existing drawi
arXiv:2604.03237v2 Announce Type: replace-cross Abstract: As AI systems increasingly support human decision making, a central challenge is determining what information helps people recognize when to r
arXiv:2608.18026v1 Announce Type: new Abstract: Large-scale, high-dimensional tabular regression remains challenging: tree-based models are robust but lack end-to-end representation learning, while de
arXiv:2505.22533v2 Announce Type: replace-cross Abstract: In this paper, we introduce a novel quantum generative model for synthesizing tabular data. Synthetic data is valuable in scenarios where real
arXiv:2608.17336v1 Announce Type: new Abstract: Long-context prefill in large language models (LLMs) incurs substantial computation and memory traffic because dense self-attention computes quadratic q
arXiv:2602.21693v2 Announce Type: replace Abstract: Multimodal time series forecasting has garnered significant attention for its potential to provide more accurate predictions than traditional single
arXiv:2608.18062v1 Announce Type: new Abstract: Language model tokenizers are typically selected with minimal evaluation, despite the fact that their design choices directly impact model capabilities.
arXiv:2510.08713v3 Announce Type: replace Abstract: Enabling embodied agents to imagine future states is essential for robust and generalizable visual navigation. Yet, state-of-the-art systems typical
arXiv:2608.17588v1 Announce Type: new Abstract: Agent Skills package reusable natural language procedures with executable resources, enabling software agents to acquire task specific capabilities with
arXiv:2608.17084v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) increasingly answer questions whose correctness depends on visual, textual, temporal, acoustic, document, chart
arXiv:2608.17268v1 Announce Type: cross Abstract: Curriculum learning has been widely adopted in the post-training of large language models by organizing training data from easy to hard. However, its
arXiv:2506.14934v2 Announce Type: replace Abstract: Distinguishing between quark- and gluon-initiated jets is a critical and challenging task in high-energy physics, pivotal for improving new physics
arXiv:2608.17530v1 Announce Type: new Abstract: Continual pre-training of large language models must acquire new information without erasing old knowledge. Existing replay methods often choose a globa
arXiv:2608.17205v1 Announce Type: new Abstract: Vision-language models (VLMs) combine images and text, but when the two conflict and one becomes harder to read, it is unclear how a model shifts its re
arXiv:2404.15616v2 Announce Type: replace-cross Abstract: Grover's search algorithms, including various Partial Grover Searches (PGS), suffer from scaling issues when multiple solutions are sought, as
arXiv:2608.14694v1 Announce Type: new Abstract: Foundation models are emerging as a transformative paradigm for AI-native sixth-generation (6G) wireless networks by enabling scalable, transferable, an
arXiv:2606.17450v2 Announce Type: replace Abstract: Traditional comorbidity scores (e.g., Charlson and Elixhauser) are widely used for risk adjustment and patient stratification, but they have two key
arXiv:2608.16402v1 Announce Type: new Abstract: Large language model-based agentic frameworks primarily optimize capability: whether an agent can reason, retrieve information, call tools, delegate wor
arXiv:2608.15975v1 Announce Type: cross Abstract: Labeling large text corpora with LLM teachers has become a practical route to training data at scale. At millions of items, hand-labeling every batch
arXiv:2608.15411v1 Announce Type: new Abstract: The ability of artificial intelligence (AI) models to generate highly realistic human voices has advanced rapidly. These technologies power accessibilit
arXiv:2606.14582v2 Announce Type: replace Abstract: Efficient route optimization play a vital role in ensuring both safety and punctuality in railway operations. It is very crucial particularly in het
arXiv:2509.20271v2 Announce Type: replace Abstract: Breast cancer is the most commonly diagnosed cancer and the leading cause of cancer-related mortality in women globally. Mammography is essential fo