Knowledge catalogue
arXiv:2605.09539v1 Announce Type: new Abstract: Multi-agent systems (MAS) have emerged as a promising paradigm for solving complex tasks. Recent work has explored self-evolving MAS that automatically
arXiv:2605.10634v1 Announce Type: new Abstract: LLM-based automatic heuristic design has shown promise for generating executable heuristics for combinatorial optimization, but existing methods mainly
arXiv:2605.10247v1 Announce Type: new Abstract: Using Large Language Models (LLMs) to process graph-structured data is an active research area, yet current state-of-the-art approaches typically rely o
arXiv:2605.09311v1 Announce Type: cross Abstract: Unlike most static material properties widely studied in the machine learning literature, ionic transport properties are inherently dynamic, making th
arXiv:2605.09922v1 Announce Type: cross Abstract: While recent self-training approaches have reduced reliance on human-labeled data for aligning LLMs, they still face critical limitations: (i) sensiti
arXiv:2605.08427v1 Announce Type: new Abstract: Self-play red team is an established approach to improving AI safety in which different instances of the same model play attacker and defender roles in
arXiv:2502.01237v3 Announce Type: replace Abstract: Direct Alignment Algorithms (DAAs) simplify LLM alignment by directly optimizing policies, bypassing reward modeling and RL. While DAAs differ in th
arXiv:2605.10851v1 Announce Type: new Abstract: We introduce the Generalized Turing Test (GTT), a formal framework for comparing the capabilities of arbitrary agents via indistinguishability. For agen
arXiv:2601.18832v3 Announce Type: replace-cross Abstract: Scaling test-time compute enhances long chain-of-thought (CoT) reasoning, yet existing approaches face a fundamental trade-off between computa
arXiv:2605.10799v1 Announce Type: cross Abstract: Corruption studies, the primary tool for evaluating chain-of-thought (CoT) faithfulness, identify which chain positions are 'computationally important
arXiv:2605.09221v1 Announce Type: cross Abstract: Fairness impossibility results often look like distinct scalar incompatibility statements. We show that several share one RKHS geometry: fairness crit
arXiv:2511.02623v2 Announce Type: replace Abstract: Post-training alignment of large language models (LLMs) relies on large-scale human annotations guided by policy specifications that change over tim
arXiv:2605.08749v1 Announce Type: new Abstract: We present the Wristband Gaussian Loss, a deterministic batch loss for Gaussianizing point embeddings without sampling, KL terms, or iterative transport
arXiv:2605.10130v1 Announce Type: new Abstract: Existing open-vocabulary detectors focus on RGB images and fail to generalize to thermal imagery, where low texture and emissivity variations challenge
arXiv:2605.10117v1 Announce Type: cross Abstract: Autonomous driving scenes range from empty highways to dense intersections with dozens of interacting road users, yet current 3D detection models appl
arXiv:2603.01960v2 Announce Type: replace-cross Abstract: TiledAttention is a scaled dot-product attention (SDPA) forward operator for SDPA research on NVIDIA GPUs. Implemented in cuTile Python (TileI
arXiv:2605.10756v1 Announce Type: new Abstract: Vision-language models enable OOD detection by comparing image alignment with ID labels and negative semantics. Existing negative-label-based methods ma
arXiv:2605.10344v1 Announce Type: new Abstract: Test-time scaling has become an effective paradigm for improving the reasoning ability of large language models by allocating additional computation dur
arXiv:2602.03688v2 Announce Type: replace Abstract: Multi-round LLM-based multi-agent systems rely on effective communication structures to support collaboration across rounds. However, most existing
arXiv:2510.20036v2 Announce Type: replace Abstract: Large language model (LLM) agents rely on external tools to solve complex tasks, but real-world toolsets often contain redundant tools with overlapp
arXiv:2509.02510v2 Announce Type: replace-cross Abstract: Large language models (LLMs), despite their impressive performance across a wide range of tasks, often struggle to balance two competing objec
arXiv:2605.08870v1 Announce Type: new Abstract: Out-of-distribution (OOD) robustness is difficult to diagnose when target-domain labels are unavailable. We consider a more restrictive source-only vari
arXiv:2605.09960v1 Announce Type: cross Abstract: Travel-time tomography forces a trade-off between mesh resolution and stability in which the regularizer choice dominates what can be recovered. We in
arXiv:2605.10772v1 Announce Type: cross Abstract: Large language-vision models (LLVM), such as OpenAI's ChatGPT and GPT-4, have gained prominence as powerful tools for analyzing text and imagery. The
arXiv:2605.09965v1 Announce Type: new Abstract: The real world unfolds along a single set of physics laws, yet human intelligence demonstrates a remarkable capacity to generalize experiences from this
arXiv:2605.10832v1 Announce Type: new Abstract: Multimodal deep search requires an agent to solve open-world problems by chaining search, tool use, and visual reasoning over evolving textual and visua
arXiv:2605.09087v1 Announce Type: cross Abstract: Audio deepfake detection systems are increasingly deployed in high-stakes security applications, yet their fairness across demographic groups remains
arXiv:2605.08128v1 Announce Type: cross Abstract: Gene Regulatory Network (GRN) inference is essential for understanding complex cellular mechanisms, rendered tractable through single-cell transcripto
arXiv:2605.10194v1 Announce Type: new Abstract: On-policy self-distillation (self-OPD) densifies reinforcement learning with verifiable rewards (RLVR) by letting a policy teach itself under privileged
arXiv:2605.09934v1 Announce Type: new Abstract: Multimodal large language models increasingly solve vision-centric tasks by calling external tools for visual inspection, OCR, retrieval, calculation, a
arXiv:2602.22779v2 Announce Type: replace Abstract: Tokenization in video models, typically through patchification, generates an excessive and redundant number of tokens. This severely limits video ef
arXiv:2605.10835v1 Announce Type: new Abstract: Optical Music Recognition (OMR), the task of transcribing sheet music into a structured textual representation, is currently bottlenecked by a lack of l
arXiv:2605.08111v1 Announce Type: cross Abstract: The widespread availability of complex time series data in various domains such as environmental science, epidemiology, and economics demands robust c
arXiv:2605.09862v1 Announce Type: cross Abstract: Graph learning research has increasingly shifted toward continual graph learning (CGL), which better reflects real-world scenarios where graphs evolve
arXiv:2605.08376v1 Announce Type: new Abstract: Underwater image enhancement (UIE) is a practically important yet underexplored application of spiking neural networks (SNNs), where the dominant degrad
arXiv:2601.08321v3 Announce Type: replace Abstract: With the rapid advancement of image generation, visual text editing using natural language instructions has received increasing attention. The main
arXiv:2605.08288v1 Announce Type: cross Abstract: Device-free localization trains models from heterogeneous wireless and visual sensors (e.g., Wi-Fi, LiDAR) distributed across edge devices. Federated
arXiv:2605.09507v1 Announce Type: new Abstract: Video summarization aims to produce a compact representation of a long video by selecting a subset of temporally important segments that best reflect hu
arXiv:2605.09276v1 Announce Type: cross Abstract: Spiking transformers have shown strong potential for neuromorphic vision, yet their token processing across multiple spiking steps still introduces su
arXiv:2605.08911v1 Announce Type: new Abstract: Autonomous vehicles need to perceive not only physical elements in the driving scene, such as lane lines and traffic lights, but also logical elements l
arXiv:2605.08709v1 Announce Type: new Abstract: Unified face attack detection (UAD) requires recognizing physical spoofing and digital forgery within a shared decision space, yet existing discriminati
arXiv:2605.08766v1 Announce Type: cross Abstract: Personalized user understanding from large-scale digital traces remains a fundamental challenge. Traditional user profiling methods rely on discrimina
arXiv:2605.10172v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have achieved remarkable success in general perception, yet complex multi-step visual reasoning remains a per
arXiv:2601.18823v3 Announce Type: replace Abstract: Variational autoencoders (VAE) encode data into lower-dimensional latent vectors before decoding those vectors back to data. Once trained, one can h
arXiv:2605.10485v1 Announce Type: new Abstract: Precise spatial reasoning is fundamental to robotic manipulation, yet the visual backbones of current vision-language-action (VLA) models are predominan
arXiv:2605.10325v1 Announce Type: new Abstract: Reinforcement learning from verifiable rewards (RLVR) has improved the reasoning abilities of large language models (LLMs), but most existing approaches
arXiv:2605.10850v1 Announce Type: new Abstract: Self-verification, re-invoking the same vision language model (VLM) in a fresh context to check its own generated answer, is increasingly used as a defa
arXiv:2605.09677v1 Announce Type: new Abstract: Reliable displacement measurement is fundamental for structural health monitoring and digital engineering workflows, as it provides direct structural re
arXiv:2605.10579v1 Announce Type: new Abstract: Training AI agents to proactively assist humans in daily activities, from routine household tasks to urgent safety situations, requires large-scale visu
arXiv:2603.13224v2 Announce Type: replace-cross Abstract: Vision-to-code tasks require models to reconstruct structured visual inputs, such as charts, tables, and SVGs, into executable or structured r
arXiv:2510.10606v4 Announce Type: replace Abstract: Post-training Large Vision-and-Language Models (LVLMs) typically involves Supervised Fine-Tuning (SFT) for knowledge injection or Reinforcement Lear
arXiv:2605.08133v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have emerged as a promising paradigm for end-to-end autonomous driving, yet their reliance on implicit parametric
arXiv:2605.10622v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have achieved remarkable progress in multimodal tasks, yet their reliability is persistently undermined by halluc
arXiv:2605.08966v1 Announce Type: new Abstract: Standard Transformers impose near-exponential decay on the influence of distant tokens, conflicting with the power-law structure of long-range dependenc
arXiv:2605.10229v1 Announce Type: new Abstract: Privacy protection has become a critical requirement in the era of ubiquitous visual data sharing, imposing higher demands on efficient and robust priva
arXiv:2605.08160v1 Announce Type: cross Abstract: Monitoring archaeological sites at scale is vital for protecting cultural heritage, yet pinpointing when disturbances occur remains difficult because
arXiv:2605.08137v1 Announce Type: cross Abstract: Weight pruning is widely advocated for deploying Large Language Models on resource-constrained IoT and edge devices, yet its impact on model fairness
arXiv:2605.08289v1 Announce Type: cross Abstract: Multivariate time series forecasting is critical in many real-world systems, and thus modeling cross-channel dependencies is essential. Although exist
arXiv:2605.08599v1 Announce Type: new Abstract: Traditional simulation methods reproduce occurred emergency instances through presetting to assist people in risk assessment and emergency decision-maki
arXiv:2605.08318v1 Announce Type: cross Abstract: We study the problem of architecture selection for deep learning models trained to solve partial differential equations (PDEs), asking when transforme