Knowledge catalogue
arXiv:2608.08211v1 Announce Type: cross Abstract: Recent low-light image enhancement (LLIE) methods have driven brightness and structural fidelity close to that of normally-exposed images, yet their o
arXiv:2608.09226v1 Announce Type: cross Abstract: Efficient text-to-image generation requires both reinforcement-learning (RL)-based reward alignment and few-step distillation, yet these procedures ar
arXiv:2608.08589v1 Announce Type: new Abstract: This paper presents RobustDefect-LLM, an industrial surface-defect inspection framework integrating deep-learning classification, operator-facing visual
arXiv:2608.09853v1 Announce Type: cross Abstract: General-purpose reward models are increasingly the bottleneck for scaling robot learning, yet the recipe for learning value-related capabilities from
arXiv:2608.09303v1 Announce Type: cross Abstract: The deployment of autonomous robotic systems in chemistry laboratories is accelerating experimental workflows and providing the foundational data for
arXiv:2608.08383v1 Announce Type: new Abstract: Steering vectors are a lightweight tool for controlling LLM behavior. However, emerging evidence shows that steering vectors can unintentionally comprom
arXiv:2608.09628v1 Announce Type: new Abstract: Collision avoidance systems are commonly used to avoid fragmentation events occurring in Low-Earth Orbit (LEO) and Geosynchronous Equatorial Orbit (GEO)
arXiv:2608.08555v1 Announce Type: new Abstract: Visible-to-infrared image translation provides a practical way to expand infrared training data using abundant visible images. Diffusion models are prom
arXiv:2509.09078v3 Announce Type: replace-cross Abstract: Given-data methods for variance-based sensitivity analysis have significantly advanced the feasibility of Sobol' index computation for computa
arXiv:2608.07945v1 Announce Type: cross Abstract: Cloud-native serverless data warehouses achieve fine-grained elasticity by decoupling storage from compute, yet determining the optimal resource alloc
arXiv:2608.07959v1 Announce Type: new Abstract: Ultra-long egocentric video understanding requires reasoning over temporally sparse evidence distributed across hours or days, challenging current multi
arXiv:2608.07531v1 Announce Type: cross Abstract: Search-augmented language agents should retrieve external information only when necessary and ground their answers in retrieved evidence. Existing ext
arXiv:2608.07553v1 Announce Type: new Abstract: Robotic manipulation often requires object specific programming, manual data annotation, or calibrated perception pipelines, which limits rapid deployme
arXiv:2512.09062v2 Announce Type: replace Abstract: Accurate 3D scene interpretation in active construction sites is essential for progress monitoring, safety assessment, and digital twin development.
arXiv:2602.17632v3 Announce Type: replace-cross Abstract: Modern offline Reinforcement Learning (RL) methods find performant actor-critics, however, fine-tuning these actor-critics online with value-b
arXiv:2608.09278v1 Announce Type: cross Abstract: GUI agents have advanced rapidly, producing a growing body of frameworks, benchmarks, and applications. However, this growth has outpaced the maturity
arXiv:2608.08200v1 Announce Type: new Abstract: Communication delay remains a central challenge in telerobotics, where it disrupts visuomotor coordination and reduces task precision. Motion scaling is
arXiv:2608.09138v1 Announce Type: cross Abstract: While learned robotic policies hold promise for advancing generalizable manipulation, their practical deployment is often hindered by suboptimal execu
arXiv:2608.09745v1 Announce Type: cross Abstract: On-policy self-distillation (OPSD) converts feedback into dense token-level supervision on trajectories generated by the policy to be optimized, provi
arXiv:2608.09867v1 Announce Type: cross Abstract: Leading large language model providers now conceal their models' step-by-step reasoning, or chain-of-thought, to protect intellectual property and lim
arXiv:2608.08326v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as an effective approach for improving multimodal reasoning. However, most existing me
arXiv:2608.00143v2 Announce Type: replace-cross Abstract: Automated attack chain generation is critical for modern cybersecurity, yet manual construction fails to scale as adversary behaviors expand.
arXiv:2608.07948v1 Announce Type: new Abstract: VAR has gained widespread popularity due to its next-scale prediction paradigm. However, it faces substantial performance bottlenecks when handling comp
arXiv:2608.07808v1 Announce Type: cross Abstract: Four years after prompt injection was first identified in 2022, attacks are still predominantly documented as verbatim strings rather than structured
arXiv:2608.07772v1 Announce Type: new Abstract: We study policy-based reinforcement learning under the mu-resets interaction protocol of Kakade and Langford [KL02]. This interaction protocol enables t
arXiv:2608.00818v2 Announce Type: replace Abstract: The discovery of scaling laws has highlighted the extraordinary potential of AI systems with a striking empirical pattern: as AI systems scale, thei
arXiv:2512.07901v4 Announce Type: replace-cross Abstract: Von Neumann founded both game theory and the theory of self-reproducing automata, but the two programs never merged. Rational players do not c
arXiv:2608.07493v1 Announce Type: cross Abstract: Current AI disclaimers often fail to function as intended due to warning habituation and a transparency paradox. As AI-generated information becomes p
arXiv:2608.07980v1 Announce Type: cross Abstract: In recent years, the term voiceprint has regained attention, particularly in technological applications and policy-making contexts, often carrying the
There are no lossless transformations of natural-language text Sophie Alpert shares her 'internal policy on acceptable use of AI writing by engineers'. It's a short read (supporting its own recommenda
arXiv:2608.08309v1 Announce Type: cross Abstract: We argue that learning visual representations without labels requires a training signal jointly complete across three non-overlapping objectives: sema
arXiv:2509.23426v3 Announce Type: replace Abstract: AI scientists are emerging computational systems that serve as collaborative partners in discovery. These systems remain difficult to build because
arXiv:2509.24039v2 Announce Type: replace-cross Abstract: If topography is a fundamental feature of the brain, it should influence both how neurons are arranged in space (i.e. explain brain maps) and
arXiv:2608.09529v1 Announce Type: new Abstract: As an important subfield of cross-modal generation, synthesizing static visual content in the form of images from audio, namely audio-to-image (A2I) gen
arXiv:2511.18721v4 Announce Type: replace-cross Abstract: The SmoothLLM defense provides a certification guarantee against jailbreaking attacks, but it relies on a strict 'k-unstable' assumption that
arXiv:2608.09052v1 Announce Type: cross Abstract: Semi-supervised adaptation of vision foundation models (VFMs) commonly freezes the pretrained backbone and updates lightweight modules such as LoRA. H
arXiv:2608.08601v1 Announce Type: new Abstract: To anticipate socio-technical risks from AI agents, organizations need taxonomies to classify them. However, existing AI risk taxonomies focus on broad
arXiv:2604.00997v2 Announce Type: replace Abstract: Reward factorization personalizes large language models (LLMs) by decomposing rewards into shared basis functions and user-specific weights. Yet, ex
arXiv:2607.16097v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become central to improving large language models (LLMs) on complex reasoning tasks, yet RL post-training is l
arXiv:2608.08359v1 Announce Type: new Abstract: Ordinal regression, also called ordinal classification, is classification of ordinal data, in which the underlying target variable is categorical and co
arXiv:2608.09098v1 Announce Type: new Abstract: End-to-end planning has shown strong promise for autonomous driving, but most existing methods are designed for structured urban roads and generalize po
arXiv:2608.08622v1 Announce Type: new Abstract: Large vision-language models (LVLMs) have demonstrated strong performance in open-ended video understanding, yet they remain prone to fluent responses u
arXiv:2608.09448v1 Announce Type: cross Abstract: Test-time training (TTT) offers a lightweight way to adapt vision--language--action (VLA) policies from unlabeled deployment streams, but it remains d
arXiv:2608.08558v1 Announce Type: new Abstract: World Action Models (WAMs) improve robot policy learning by jointly modeling future visual dynamics and actions. However, their scalability and generali
arXiv:2608.08569v1 Announce Type: new Abstract: Recent advancements in Speech Large Language Models have demonstrated remarkable capabilities in understanding complex audio tasks. Despite this progres
arXiv:2608.09447v1 Announce Type: cross Abstract: On-policy distillation (OPD) aligns a student with a teacher on trajectories sampled from the student itself, reducing the train-test state mismatch o
arXiv:2608.08453v1 Announce Type: new Abstract: Under the current standard, Agent Skills are SKILL.md files that combine instructions with supporting resources, enabling Large Language Model (LLM) age
arXiv:2608.07911v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models have outgrown accelerator memory, and offloading expert weights to host memory is now standard. This makes expert cache
arXiv:2608.07786v1 Announce Type: new Abstract: Open-weight large language models (LLMs) are increasingly developed through complex, multi-stage pipelines, leading to intricate lineage relationships t
arXiv:2608.09730v1 Announce Type: new Abstract: Vision-language-action (VLA) models are a widely adopted paradigm for embodied policies. They excel at efficient closed-loop control but do not explicit
arXiv:2608.08471v1 Announce Type: new Abstract: Deployed LLM safety guardrails are predominantly static: trained once and frozen at release, while new jailbreak techniques and previously un-addressed
arXiv:2606.15059v2 Announce Type: replace Abstract: Simultaneous speech-to-speech translation (SimulS2ST) enables real-time cross-lingual communication, but existing evaluation has focused largely on
arXiv:2608.07193v1 Announce Type: cross Abstract: Visual-token pruning can substantially reduce the inference cost of multimodal large language models (MLLMs), yet existing methods largely rely on fix
arXiv:2608.07065v1 Announce Type: cross Abstract: Action-chunking visuomotor policies learn from demonstrations and improve temporal consistency by predicting short action sequences rather than single
arXiv:2608.06609v1 Announce Type: new Abstract: Automated item evaluation (AIE) refers to the use of computational methods to assess item quality without requiring manual expert review or field testin
arXiv:2608.06996v1 Announce Type: new Abstract: This paper presents a sensor-minimal automated assembly system for bidirectional single-row flat ribbon cable harnesses (FRCHs). Unlike conventional peg
arXiv:2608.07419v1 Announce Type: new Abstract: Preference alignment often makes large language models (LLMs) overconfident and poorly calibrated. Traditional post-hoc temperature scaling is inherentl
arXiv:2608.06727v1 Announce Type: new Abstract: Transformer models for high-dimensional omics analysis process thousands of genes or pathways, although only a subset requires deep computation. Mixture
arXiv:2608.06940v1 Announce Type: new Abstract: LLM judge panels are a standard evaluation tool, but prior work reports highly correlated panel errors: nine judges provide roughly the effective inform
arXiv:2608.06559v1 Announce Type: new Abstract: Contextual bandits offer a natural framework for sample-efficient personalization, but practical deployment remains difficult under sparse, biased inter