Knowledge catalogue
arXiv:2608.02786v1 Announce Type: new Abstract: AI systems can fail silently. The failure propagates through training loops, evaluation pipelines, and production monitoring stacks until downstream har
arXiv:2608.02966v1 Announce Type: new Abstract: Most multiple-choice question (MCQ) benchmarks evaluate Large Language Models (LLMs) only by whether they select the correct answers. This binary scorin
arXiv:2608.03872v1 Announce Type: new Abstract: Human-in-the-loop reinforcement learning (HIL-RL) enables robots to learn contact-rich manipulation from limited real-world interaction, but deployment
arXiv:2608.03733v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have achieved remarkable performance across vision-language tasks, but their progress depends heavily on large-
arXiv:2608.03106v1 Announce Type: new Abstract: Infrared image super-resolution (IISR) is important for downstream tasks such as object detection and semantic segmentation. Existing IISR methods often
arXiv:2608.03096v1 Announce Type: cross Abstract: Recent advances in video generation models have significantly intensified the deepfake threat, yet the current deepfake video detection benchmarks rem
arXiv:2608.02806v1 Announce Type: cross Abstract: By leveraging data from video-based perception systems, intelligent transportation systems (ITS) support safety-critical applications that improve roa
arXiv:2608.02919v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in complex, compound AI systems where performance hinges on the quality of prompts. Recent state-
arXiv:2608.03822v1 Announce Type: cross Abstract: Developing robust flood assessment models requires high-quality paired satellite imagery, yet such data remain scarce for flood-specific image generat
arXiv:2608.03609v1 Announce Type: new Abstract: Agentic systems driven by large language models (LLMs) are increasingly deployed in real-world workflows where they act on persistent operational data.
arXiv:2608.03385v1 Announce Type: new Abstract: Existing object detection methods predominantly utilize sRGB inputs, which are compressed from RAW sensor data using Image Signal Processors (ISP) origi
arXiv:2508.00955v3 Announce Type: replace-cross Abstract: Adapting generative Multimodal Large Language Models (MLLMs) into universal embedding models typically demands resource-intensive contrastive
arXiv:2608.03143v1 Announce Type: new Abstract: Vision-and-Language Navigation (VLN) requires an agent to follow a route-level instruction by executing its constituent steps from egocentric visual obs
arXiv:2608.03868v1 Announce Type: cross Abstract: Causal Discovery (CD) from observational data faces two fundamental challenges. First, purely statistical methods often lack the power to resolve stru
arXiv:2608.03923v1 Announce Type: new Abstract: Codebook-based blind face restoration (BFR) often suffers from ambiguous conditioning features and a fragile prediction mechanism under severe degradati
arXiv:2608.03618v1 Announce Type: new Abstract: Inferring complete 3D geometry and semantics from onboard images remains challenging because occlusions and restricted fields of view leave large scene
arXiv:2608.03071v1 Announce Type: new Abstract: Large language model agents derive much of their capability from tool use. Existing research on tool use has largely focused on selecting the right tool
arXiv:2608.02690v1 Announce Type: new Abstract: On-device training of deep neural networks is fundamentally constrained by the computational and memory costs of large-scale datasets. Coreset selection
arXiv:2608.03753v1 Announce Type: new Abstract: Learning long-horizon manipulation skills with reinforcement learning remains challenging due to the complexity of reward design, the limited guidance o
arXiv:2608.03083v1 Announce Type: cross Abstract: Video large language models (VideoLLMs) achieve strong video understanding performance, but their inference remains expensive due to the large number
arXiv:2608.03270v1 Announce Type: cross Abstract: GUI grounding maps natural-language instructions to click locations and is essential for reliable GUI agents. The task remains difficult on high-resol
arXiv:2601.03321v3 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have substantially advanced Radiology Report Generation (RRG), yet aligning them through reinforcemen
arXiv:2608.03545v1 Announce Type: new Abstract: Test-time reinforcement learning (TTRL) improves the reasoning capabilities of large language models without labeled data by updating the policy with ps
arXiv:2608.03511v1 Announce Type: cross Abstract: Active learning (AL) promises to reduce the cost of medical imaging projects by lowering the number of clinical labels required. However, practical de
arXiv:2608.02650v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly rely on external tools to complete complex real-world tasks. However, reliable tool-use planning remains
arXiv:2608.02930v1 Announce Type: new Abstract: We revisit higher-arity atomic concept learning through the geometry of hypercubes and hyperplanes of ground instances. Our starting point is the observ
arXiv:2608.02967v1 Announce Type: cross Abstract: Software fault localization identifies the code locations responsible for reported issues and is a fundamental step toward automated debugging and pro
arXiv:2608.03210v1 Announce Type: new Abstract: Foundation models have achieved remarkable success across diverse tasks, but they remain vulnerable. To investigate such vulnerabilities, semantic-shift
arXiv:2608.03216v1 Announce Type: new Abstract: Query-based mask transformers assemble segmentation outputs through pixel-wise competition among query predictions of the final layer, yet this inferenc
arXiv:2503.13077v2 Announce Type: replace Abstract: Multi-agent reinforcement learning has shown promise in learning cooperative behaviors in team-based environments. However, such methods often deman
arXiv:2608.02986v1 Announce Type: cross Abstract: A software agent on a public blockchain accumulates authority and economic stakes, raising the engineering question of what makes it count as an indiv
arXiv:2608.03138v1 Announce Type: cross Abstract: Generating a rigorous paper introduction with large language models (LLMs) remains challenging, since it requires coordinating background, gap identif
arXiv:2608.02879v1 Announce Type: new Abstract: The widespread adoption of proprietary Large Language Models (LLMs) accessed strictly through closed APIs has created a critical challenge for responsib
arXiv:2507.14171v3 Announce Type: replace-cross Abstract: Importance-based structured pruning overwhelmingly relies on filter magnitude. This proxy is fundamentally flawed: due to scale invariance, fu
arXiv:2608.03974v1 Announce Type: new Abstract: Real-time video editing requires low-latency causal generation with bounded computational resources while preserving source fidelity and long-term tempo
arXiv:2608.03681v1 Announce Type: new Abstract: Zero-shot visual anomaly detection has achieved remarkable progress, with recent vision-only approaches further improving performance while simplifying
arXiv:2608.03838v1 Announce Type: new Abstract: Reasoning-based guard models improve LLM safeguards, but decoding explicit rationales for every interaction makes them costly to deploy. Although latent
arXiv:2608.03463v1 Announce Type: new Abstract: Long-term memory is essential for LLM-based agents to sustain interactions and reliably leverage distant history. However, existing memory systems typic
arXiv:2608.03234v1 Announce Type: new Abstract: Motion priors provide powerful guidance for learning naturalistic humanoid behaviors. However, existing methods typically learn a general, task-agnostic
arXiv:2608.02688v1 Announce Type: cross Abstract: Phenotypic drug discovery enables the discovery of functional relationships between molecular structures and cellular responses. However, existing mul
arXiv:2608.03050v1 Announce Type: cross Abstract: What is music style? Though often described using text labels such as 'swing,' 'classical,' or 'emotional,' the real style remains implicit and hidden
arXiv:2608.03490v1 Announce Type: cross Abstract: 3D object detection using light detection and ranging (LiDAR) sensors requires a balance between accuracy and computational efficiency for onboard per
arXiv:2608.03851v1 Announce Type: new Abstract: Real-time 3D perception is crucial for robotics, augmented reality, and embodied intelligence applications. Existing multi-view stereo (MVS) methods pri
arXiv:2608.03330v1 Announce Type: new Abstract: This thesis addresses fundamental challenges in traffic scene prediction for autonomous driving by introducing robust and computationally efficient mode
arXiv:2608.03844v1 Announce Type: new Abstract: Memory-augmented LLM agents rely on rich context for long-horizon reasoning and acting, yet their memory modules expose a persistent attack surface for
arXiv:2405.16440v2 Announce Type: replace-cross Abstract: In recent years, Transformers have become the de-facto architecture for long-term time series forecasting (LTSF), yet they face challenges ass
arXiv:2608.02971v1 Announce Type: new Abstract: Language models often complete an underspecified reference to a city with unstated assumptions about urban size, form, infrastructure, environment, and
arXiv:2502.06606v3 Announce Type: replace Abstract: Manipulating the material appearance of objects in images is critical for applications like augmented reality, virtual prototyping, and digital cont
arXiv:2203.17257v2 Announce Type: replace Abstract: Salient Object Ranking (SOR) aims to estimate the relative saliency order among multiple salient objects. While SOR has been extensively studied in
arXiv:2603.15212v2 Announce Type: replace Abstract: Evaluating football player transfers is challenging because player actions depend strongly on tactical systems, teammates, and match context. Despit
arXiv:2606.15615v2 Announce Type: replace-cross Abstract: Diffusion Transformers with Mixture-of-Experts (DiT-MoE) improve model capacity under sparse activation, but diffusion inference is still bott
arXiv:2608.03275v1 Announce Type: new Abstract: Parameter-efficient fine-tuning (PEFT) enables efficient adaptation of large language models, but existing MoE-based PEFT methods typically improve capa
arXiv:2608.03664v1 Announce Type: new Abstract: Accurate diagnosis in Digital Pathology (DP) relies on high-resolution whole-slide images, yet clinical deployment is often limited by hardware costs. S
arXiv:2608.02674v1 Announce Type: cross Abstract: With the widespread deployment of large foundation models (LFMs) in open environments, safety threats are shifting from black-box jailbreaks toward wh
arXiv:2402.13822v2 Announce Type: replace Abstract: Most of the previous approaches to Time Series Classification (TSC) highlight the significance of receptive fields and frequencies while overlooking
arXiv:2608.03708v1 Announce Type: new Abstract: Text-to-image diffusion models enable personalization of specific visual concepts from a small number of reference images. However, generating a single
arXiv:2608.03885v1 Announce Type: new Abstract: Vision-language models exhibit remarkable zero-shot capabilities but suffer significant performance degradation under distribution shifts. While test-ti
arXiv:2608.02700v1 Announce Type: cross Abstract: Analog compute-in-memory (CIM) enables energy-efficient neural network inference, but device variation and read noise can severely degrade low-bit qua
arXiv:2604.01973v2 Announce Type: replace Abstract: When evaluating identity-focused tasks such as personalized generation and image editing, existing vision encoders entangle object identity with bac
arXiv:2608.03113v1 Announce Type: new Abstract: Adulteration of bovine milk using urea remains a major food quality and health concern, motivating the development of rapid and quantitative screening t