Knowledge catalogue
arXiv:2501.09731v2 Announce Type: replace-cross Abstract: We establish a formal connection between the decades-old surrogate outcome model in biostatistics and economics and the emerging field of pred
arXiv:2606.22878v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly deployed at the network edge to provide pervasive generative AI services, decentralized federated learn
arXiv:2606.20512v2 Announce Type: replace-cross Abstract: LLM-based coding agents need higher-level operational knowledge about a repository (which files house which subsystems, how to run the test su
arXiv:2606.22914v1 Announce Type: new Abstract: Activities in numerous evolving systems can be represented as dynamic graphs in snapshot form at different time intervals, i.e., discrete-time dynamic g
arXiv:2606.21876v1 Announce Type: new Abstract: The Categorical Jacobian (CJ) of Zhang et al. (2024) reads protein contacts from a language model by perturbing every residue with every alternative ami
arXiv:2606.20913v1 Announce Type: new Abstract: Medical vision-language models (VLMs) enable zero-shot clinical image classification, yet reliably detecting out-of-distribution (OOD) inputs at deploym
arXiv:2606.22421v1 Announce Type: new Abstract: Hyperdimensional Computing (HDC) is a robust computational framework inspired by human cognition characterized by simple and efficient operations within
arXiv:2511.18689v4 Announce Type: replace Abstract: Kolmogorov--Arnold Networks (KANs) replace linear weights with spline-based functions, offering strong expressivity but posing challenges for low-pr
arXiv:2606.21011v1 Announce Type: new Abstract: We present R2HandoverSim, a simulation benchmark for robot-to-human (R2H) object handovers. Although R2H handover methods have advanced rapidly, the lac
arXiv:2606.22766v1 Announce Type: new Abstract: Audio Description aims to generate concise narrations of essential visual content in audio-visual media for blind and low-vision audiences. Existing met
arXiv:2603.04205v2 Announce Type: replace Abstract: While Vision-Language Models (VLMs) achieve near-perfect scores on digital document benchmarks like OmniDocBench, their performance in the unpredict
arXiv:2606.22166v1 Announce Type: cross Abstract: Author rebuttals are the main post-submission window in peer review, but their effect on reviewer scores remains hard to measure because score updates
arXiv:2512.21988v3 Announce Type: replace-cross Abstract: Background: Smartphone-based dermatology requires inter-device colorimetric reliability that holds across calibration regimes, yet quantitativ
arXiv:2606.22402v1 Announce Type: cross Abstract: Large language model (LLM)-based approaches for automated code compliance (ACC) of building regulations are prone to generating incorrect and hallucin
arXiv:2606.20736v1 Announce Type: new Abstract: Static visual question answering (VQA) benchmarks age quickly: Once the items leak into training corpora, scores can reflect memorization rather than ge
arXiv:2606.23104v1 Announce Type: new Abstract: On-policy distillation (OPD) improves LLM reasoning by training a student model on its own generated outputs, but standard OPD treats all student-genera
arXiv:2606.22181v1 Announce Type: new Abstract: Deep allergenicity classifiers are increasingly used in safety screening of novel foods, and recent protein language models have substantially improved
arXiv:2409.05755v3 Announce Type: replace Abstract: Over the past decade, Graph Neural Networks (GNNs) have achieved great success on machine learning tasks with relational data. However, recent studi
arXiv:2511.07272v2 Announce Type: replace Abstract: Overparameterized fully-connected neural networks have been shown to behave like kernel models when trained with gradient descent, assuming standard
arXiv:2606.20959v1 Announce Type: new Abstract: Large language models can store both outdated facts and newer superseding facts in their parameters, but standard prompting may still elicit the outdate
arXiv:2606.22840v1 Announce Type: new Abstract: We present RLM-Cascade, a proxy-layer system that applies speculative decoding at the response level to reduce LLM API costs without requiring model arc
arXiv:2511.23221v2 Announce Type: replace Abstract: In this paper, we challenge the conventional notion in 3DGS-SLAM that rendering quality is the primary determinant of tracking accuracy. We argue th
arXiv:2606.18774v2 Announce Type: replace Abstract: We present RouteJudge, an online pairwise preference evaluation framework for LLM routing systems, with a public platform available at https://route
arXiv:2606.21755v1 Announce Type: new Abstract: Pre-Phase-A design of lunar micro-rovers is dominated by tightly coupled mobility, power, thermal, and mass trades, yet conceptual-design tooling for th
arXiv:2606.23221v1 Announce Type: new Abstract: Recent years have witnessed remarkable progress in image generation and editing, particularly regarding instruction following and visual fidelity. Howev
arXiv:2606.23344v1 Announce Type: new Abstract: Accurate document layout analysis remains a critical bottleneck for document parsing systems, due to the intricate coupling among heterogeneous document
rumors of new models being delayed 🚨 SCOOP(s): - GPT-5.6 has been delayed and will no longer release this week. New target is ~mid-July. - DeepMind are not satisfied with the current state of 3.5 Pro
arXiv:2606.22248v1 Announce Type: new Abstract: Standard autoregressive Transformer decoders can often exhibit substantial forgetting under sequential fine-tuning on shifting curriculum distributions.
arXiv:2606.22694v1 Announce Type: new Abstract: Vision-Language Models (VLMs) remain unreliable when spatial reasoning requires composing relations whose meanings depend on frames of reference. Existi
arXiv:2606.23607v1 Announce Type: new Abstract: Linear mode connectivity (LMC) provides a promising foundation for understanding and merging independently trained neural networks, but existing methods
arXiv:2505.17295v2 Announce Type: replace Abstract: We introduce ScanBot, a benchmark for instruction-conditioned, high-precision surface scanning with robot-mounted industrial laser profilers. Unlike
arXiv:2606.23101v1 Announce Type: new Abstract: ALS boresight calibration has relied for two decades on dedicated flight patterns over structured scenes containing planar surfaces of varied aspect and
arXiv:2606.22568v1 Announce Type: new Abstract: Training image generation foundation models consumes substantial resources. Previous methods have attempted to leverage semantic guidance to accelerate
arXiv:2606.17702v2 Announce Type: replace Abstract: Characterising the tumour microenvironment (TME) from routine H&E-stained histology images requires simultaneous cell segmentation, feature extracti
arXiv:2606.22350v1 Announce Type: new Abstract: Reinforcement Learning (RL) has been widely applied to sequential decision-making, yet it often suffers from poor sample efficiency due to costly intera
arXiv:2606.23112v1 Announce Type: new Abstract: Multi-turn tool-using agents must coordinate long-horizon tool sequences while tracking dialogue state and policy constraints. Existing approaches often
arXiv:2606.21090v1 Announce Type: cross Abstract: Self-improvement can self-regress. In REINFORCE post-training for code, a model can quickly improve on its optimized metric and then collapse within t
arXiv:2606.22210v1 Announce Type: new Abstract: One of the powerful techniques in data modeling is accounting for features that are available at the training stage, but are not available when the trai
arXiv:2602.22747v2 Announce Type: replace Abstract: Epistemic uncertainty in neural networks is commonly modeled using two second-order paradigms: distribution-based representations, which rely on pos
arXiv:2606.18487v2 Announce Type: replace Abstract: The standard heuristic of selecting the SFT checkpoint with the highest pass@1 for GRPO can fail when SFT compresses the rollout distribution. For b
arXiv:2606.22873v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly deployed in consumer, medical, financial, and enterprise applications. This broad deployment expands the
arXiv:2606.20659v1 Announce Type: cross Abstract: Agent skills encode reusable procedural knowledge that guides large language model agents across tasks and execution contexts. Existing evaluations pr
arXiv:2606.14150v2 Announce Type: replace Abstract: Pruning promises a shortcut to strong small language models. In this work, we examine this promise by pruning Llama-3.1-8B at pruning ratios of 0.5-
Cybersecurity company Snyk Ltd. today launched Evo Agentic Development Security, a new layer of its artificial intelligence security platform built to police the autonomous coding agents that increasi
arXiv:2606.21356v1 Announce Type: new Abstract: Many machine learning applications rely on heterogeneous event streams to make predictions, either causally as events arrive or bidirectionally over com
arXiv:2605.24354v2 Announce Type: replace Abstract: Recently, world models have made significant progress in enhancing end-to-end driving systems through both future situation forecasting and improved
arXiv:2606.20629v1 Announce Type: cross Abstract: LLM agents are increasingly deployed as multi-role teams, where tasks are divided across specialized roles such as planner, executor, and verifier. In
arXiv:2606.21811v1 Announce Type: cross Abstract: End-to-end code agent training is resource-intensive and plateaus on the strategy-level reasoning needed to resolve code issues, since jointly optimiz
arXiv:2503.22087v3 Announce Type: replace Abstract: In this paper, we explore dense voxel streaming for accurate and efficient 3D occupancy prediction. While dense voxel representations offer fine-gra
arXiv:2510.17385v5 Announce Type: replace Abstract: Tabular prediction has long been dominated by gradient-boosted decision trees and specialized deep tabular models, while large language models (LLMs
arXiv:2606.22383v1 Announce Type: new Abstract: Parameter-efficient fine-tuning (PEFT) has become a practical solution for adapting large pretrained vision transformers (ViTs) to downstream tasks whil
arXiv:2606.22606v1 Announce Type: cross Abstract: Large language models (LLMs) achieve strong relation extraction (RE), but their computational demands and reliance on proprietary APIs limit deploymen
arXiv:2606.22986v1 Announce Type: new Abstract: This work studies subject recognition from Leap Motion Controller 2 (LMC2) hand landmark data under a subject-level unknown-identity identification prot
arXiv:2606.23568v1 Announce Type: new Abstract: Large language models (LLMs) achieve remarkable performance across a wide range of tasks, but their deployment is constrained by substantial memory and
arXiv:2606.22339v1 Announce Type: new Abstract: Recent advances in vision-language models and generative editing systems have made it increasingly easy to produce persuasive multimodal misinformation
Tag Claude in a channel, it spins up an instance with its own sandbox. It clones repos, writes code, tests, compiles all in that isolated environment and the sandbox gets thrown away when it's done. O
arXiv:2603.21478v2 Announce Type: replace-cross Abstract: Speech technologies have advanced rapidly and serve diverse populations worldwide. However, many languages remain underrepresented due to limi
arXiv:2606.23670v1 Announce Type: new Abstract: Modern language models, including transformer, recurrent, and memory-based variants, share a common chassis: a stack of identical layers in which parame
arXiv:2606.22775v1 Announce Type: cross Abstract: Distribution shift between training and deployment is a pervasive challenge for modern AI systems. In many cases, the target marginals of covariates a
arXiv:2606.21307v1 Announce Type: new Abstract: Continual learning (CL) is commonly studied under the assumption that sequential tasks are semantically related or structurally similar. However, in hig