Knowledge catalogue
arXiv:2603.23118v2 Announce Type: replace Abstract: Recent works have shown that multimodal large language models (MLLMs) are highly vulnerable to hidden-pattern visual illusions, where the hidden con
arXiv:2607.26788v1 Announce Type: cross Abstract: Clustered federated learning benefits from organizing heterogeneous participants into coalitions that train coalition-specific models, but such cluste
arXiv:2607.26228v1 Announce Type: new Abstract: Instruction hierarchies are a core safety assumption of language model deployment: higher priority inputs, such as system prompts, should override confl
arXiv:2607.26985v1 Announce Type: cross Abstract: Deep reinforcement policy learning directly in physical robots (on-robot learning) remains bottlenecked by slow wall-clock training times. We present
arXiv:2509.05130v2 Announce Type: replace Abstract: In classification problems, models are trained to predict a class label based on the input data features. However, class labels are organized hierar
// The agent is its own best speculator // Agents spend a large share of wall-clock time waiting on tool results. Speculation hides that latency by predicting and pre-executing the next call, but exte
arXiv:2607.26309v1 Announce Type: cross Abstract: Estimating causal effects of linguistic properties from observational text is difficult because the same document can contain both the treatment of in
The narrative: Blame the Agent, instead of the Agency that told him to “apply all your powers and told to achieve this win.” Ironically, many forefront members of the AI-Safety community, in their fer
arXiv:2607.26845v1 Announce Type: new Abstract: Inference-time thinking improves the performance of large language models, but aggregate outcomes do not reveal whether models use available evidence mo
arXiv:2607.27122v1 Announce Type: new Abstract: Gastrointestinal (GI) endoscopic image analysis has shifted from single-label classification toward visual question answering (VQA), where a model must
arXiv:2607.26107v1 Announce Type: new Abstract: Dense vision-language understanding, including object localization, region recognition, and open-vocabulary semantic segmentation, requires associating
arXiv:2607.27113v1 Announce Type: new Abstract: The growing capability of image generation models has made synthetic images a routine presence in open media, making robust and generalizable AI-Generat
arXiv:2512.01280v2 Announce Type: replace Abstract: Autonomous aerial tracking with drones offers vast potential for surveillance, cinematography, and industrial inspection applications. While single-
arXiv:2607.26246v1 Announce Type: new Abstract: On-policy distillation (OPD), which aligns a student with the teacher's token-level distribution on the student's own rollouts, is an effective paradigm
arXiv:2607.26604v1 Announce Type: new Abstract: Knowledge-base construction and querying are typically optimized in isolation: retrieval-augmented agents operate over a fixed, externally maintained in
arXiv:2410.24035v2 Announce Type: replace-cross Abstract: Generating robust and reactive manipulation strategies that can adapt to changing context information is a challenging task in robotics. Over
arXiv:2503.05632v2 Announce Type: cross Abstract: In many image analysis problems, the contours of objects carry important statistical information about shape. Such contours are typically affected by
arXiv:2607.25207v1 Announce Type: new Abstract: This paper investigates a hybrid reinforcement learning setting in tabular Markov Decision Processes (MDPs), where an agent aims to learn an optimal pol
arXiv:2004.06320v2 Announce Type: replace Abstract: Research in machine learning, mobile robotics, and autonomous driving is accelerated by the availability of high quality annotated data. To this end
arXiv:2607.24833v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards is a powerful paradigm for eliciting reasoning in large language models, yet it suffers from severe rewar
arXiv:2607.25489v1 Announce Type: new Abstract: Large language models and multimodal foundation models are enabling medical artificial intelligence (AI) systems to move beyond isolated prediction and
arXiv:2605.05580v2 Announce Type: replace Abstract: Quantitative trading agents have demonstrated substantial promise in automating factor discovery, signal aggregation, and portfolio execution. Howev
arXiv:2607.25479v1 Announce Type: cross Abstract: Vision--Language Models (VLMs) are increasingly deployed through a model supply chain in which pretrained checkpoints, architecture definitions, text
arXiv:2607.24881v1 Announce Type: new Abstract: As system complexity has vastly increased, it has become significantly more challenging for a single person or a team to fully understand all aspects of
arXiv:2607.24848v1 Announce Type: cross Abstract: Pretrained molecular encoders are commonly evaluated through downstream prediction, but predictive accuracy alone does not establish that a learned re
arXiv:2607.25600v1 Announce Type: cross Abstract: Retrieval-augmented generation improves knowledge-intensive question answering, but indiscriminate retrieval can introduce irrelevant evidence and unn
arXiv:2602.10430v2 Announce Type: replace-cross Abstract: Off-policy policy optimization reuses historical behavior, including negative-advantage samples that suppress known failures. We show that rep
arXiv:2607.24996v1 Announce Type: cross Abstract: Neural networks are hindered by accumulating dormant neurons and loss of expressivity throughout training, particularly in non-stationary data setting
arXiv:2607.25308v1 Announce Type: cross Abstract: Training large language models (LLMs) to act in long-horizon games is a promising step toward generalist decision-making, yet reinforcement learning w
arXiv:2509.11285v2 Announce Type: replace-cross Abstract: Class-Incremental Learning (CIL) in deep neural networks is conventionally framed as an iterative gradient-based optimization problem, incurri
arXiv:2607.25633v1 Announce Type: cross Abstract: Large language models (LLMs) are costly intellectual assets that remain exposed to unauthorized redistribution and commercial misuse. Injected fingerp
arXiv:2607.25408v1 Announce Type: new Abstract: A growing body of 2026 work applies control theory to LLM agents: Lyapunov-certified stability for tool-mediated controllers (Prinos et al., 'Stable Age
arXiv:2607.25664v1 Announce Type: new Abstract: Machine learning demand forecasts optimize statistical accuracy yet leave excess operational volatility that inflates safety stock and amplifies the Bul
arXiv:2607.25283v1 Announce Type: new Abstract: This paper presents ContractHIL-HLS, a contract-aligned multi-agent workflow for practical high-level synthesis (HLS) engineering. The workflow makes th
arXiv:2510.07884v3 Announce Type: replace-cross Abstract: Weak-to-strong generalization provides a promising paradigm for scaling large language models (LLMs) by training stronger models on samples fr
arXiv:2607.25659v1 Announce Type: new Abstract: Rubric-based reinforcement learning enriches language model training by evaluating model outputs against explicit criteria. Yet in GRPO-style pipelines,
arXiv:2607.25480v1 Announce Type: new Abstract: Constrained online convex optimization requires minimizing regret against adversarial convex costs while satisfying a convex constraint at every round,
arXiv:2511.20992v2 Announce Type: replace Abstract: Behavior Cloning (BC) is a popular framework for training sequential decision policies from expert demonstrations via supervised learning. As these
arXiv:2607.24785v1 Announce Type: cross Abstract: Efficient exploration of the photonic crystal (PhC) lattice design space is essential for developing photonic crystal surface-emitting lasers. While c
arXiv:2607.25195v1 Announce Type: new Abstract: Efficient autonomous exploration with palm-sized nano-UAVs remains challenging due to severe limitations in sensing, computation, and flight endurance.
arXiv:2607.25465v1 Announce Type: new Abstract: Video saliency models typically apply a single fixation strategy across crowd scenes, despite systematic changes in attention with crowd density. Sparse
arXiv:2607.24758v1 Announce Type: new Abstract: Large language models are capable of recognizing evaluation contexts and altering their behavior to reflect evaluator expectations rather than typical d
arXiv:2607.25995v1 Announce Type: cross Abstract: Kubernetes is central to the cloud-native ecosystem, orchestrating containerised workloads. Recent work suggests that large language models (LLMs) can
arXiv:2601.21409v3 Announce Type: replace Abstract: Adaptive navigation in unfamiliar indoor environments is crucial for household service robots. Despite advances in zero-shot perception and reasonin
arXiv:2607.24893v1 Announce Type: cross Abstract: Multi-agent LLM systems can be attacked by a payload that no single agent ever holds in full: a poisoned tool hides encrypted fragments in its observa
arXiv:2607.24860v1 Announce Type: new Abstract: Approaching a target position and holding station in flowing water is a fundamental and critical capability for robotic fish operating in natural aquati
arXiv:2607.25814v1 Announce Type: new Abstract: The emergence of the recent outstanding capabilities of Arabic Language Models has opened doors for exposing their vulnerabilities. One of the major sec
arXiv:2607.25581v1 Announce Type: new Abstract: Code-mixed speech poses unique challenges to forced alignment: expanded inventories, orthographic errors, and speaker variation. We evaluate forced alig
arXiv:2607.25364v1 Announce Type: new Abstract: Tool-using agents expose structured calls but commonly attach free-form rationales. Such rationales are neither authorization nor reliable introspection
arXiv:2607.25926v1 Announce Type: cross Abstract: Face de-identification (De-ID) aims to remove or conceal personally identifiable facial features in images or videos to prevent identity recognition w
arXiv:2502.11049v3 Announce Type: replace Abstract: Automated Facial Expression Recognition (FER), involves two critical aspects: data and model design. Both significantly influence bias and fairness
arXiv:2507.11548v3 Announce Type: replace-cross Abstract: The use of publicly available generative AI systems for resume evaluation is often justified by the assumption that these tools reduce bias re
arXiv:2607.26034v1 Announce Type: new Abstract: Technological races create tension between speed and safety: actors may gain by moving faster than competitors, even when risky development is harmful.
arXiv:2607.25794v1 Announce Type: new Abstract: Fine-grained food visual--semantic understanding requires models to capture subtle distinctions across ingredients, cooking methods, doneness, color, te
arXiv:2607.25423v1 Announce Type: cross Abstract: Eliciting explainable AI (XAI) requirements from stroke survivors presents a methodological challenge with direct implications for the design of trust
Gary Marcus has argued that both OpenAI and Anthropic must increase their pricing, citing the rapid decline in token costs and competition from open‑source models. He presents a binary choice: either
arXiv:2607.25503v1 Announce Type: new Abstract: Computational cytology on whole-slide images is challenging because malignant cells are rare, heterogeneous, and annotated slides are scarce. Anomaly de
arXiv:2508.05775v3 Announce Type: replace Abstract: Large Language Models (LLMs) have revolutionized content creation across digital platforms, offering unprecedented capabilities in natural language
Gary Marcus shared a “handy dandy AI crisis flowchart” created by Kate Klonick (@Klonick) on Saturday, July 28. The tweet also notes that he had planned to write an article about Hugging Face and Open
arXiv:2607.25297v1 Announce Type: cross Abstract: The rapid development of large language model (LLM) agents has enabled their broad adoption across diverse real-world tasks. To standardize interactio