Knowledge catalogue
arXiv:2609.00232v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved strong performance on OCR-centric document understanding and text-rich visual reasoning benchmark
arXiv:2609.00605v1 Announce Type: cross Abstract: Machine unlearning for large language models (LLMs) often assumes that a pre-defined forget set matches what the model has memorized, but this frequen
arXiv:2609.01161v1 Announce Type: new Abstract: Large language models can reproduce memorized text verbatim, yet copyright defenses are usually evaluated under incompatible protocols. We introduce Cop
arXiv:2609.00366v1 Announce Type: cross Abstract: High test accuracy and good aggregate calibration do not show whether an individual prediction is structurally supported by its evidence. In tabular d
arXiv:2609.00683v1 Announce Type: new Abstract: Creative generation tasks, such as narrative writing and scientific ideation, demand both high-quality outputs and distinct responses across independent
arXiv:2609.00206v1 Announce Type: cross Abstract: Despite their growing use in video moderation, multimodal large language models (MLLMs) exhibit a compositional safety blind spot: videos composed of
arXiv:2609.00177v1 Announce Type: cross Abstract: General-purpose NLP embedding models perform well on linguistic tasks, but their ability to capture symbolic ontological structure remains unclear. We
arXiv:2609.01404v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) are strong perceivers of images and video. We ask how far that reach extends into acting: dropping an MLLM di
arXiv:2609.00994v1 Announce Type: new Abstract: Recent extensions of 3D Gaussian Splatting (3DGS) enable real-time novel view synthesis in dynamic scenes by learning time-conditioned Gaussian deformat
arXiv:2609.00474v1 Announce Type: cross Abstract: LLMs are increasingly deployed as orchestrators that coordinate specialized subagents to solve complex tasks through natural language. However, in man
Finally, a good paper testing if graph memory actually beats flat retrieval for long-term agents. (bookmark this one) Researchers extract each conversational turn into typed nodes and attributed edges
Further evidence for @GaryMarcus 's worries about the security competence of the people running AI. Vibe coding without then checking security is not impressive 🚨 Attackers stole a METR API key and us
arXiv:2609.01106v1 Announce Type: cross Abstract: When a hint turns a failing generated program into a passing one, does it provide missing information or merely steer the model toward a solution it c
arXiv:2607.18114v2 Announce Type: replace-cross Abstract: Modern LLMs are alarmingly susceptible to surprisingly simple immaterial changes of input prompts: a casual hint, an incorrectly labeled few-s
arXiv:2609.01532v1 Announce Type: new Abstract: Logit-based knowledge distillation (KD) is used to train smaller language models (LMs) via supervision from stronger teachers, but whether its benefits
arXiv:2609.01072v1 Announce Type: cross Abstract: Post-hoc calibration corrects reported confidence, yet a multiclass calibrator can also change the associated top-1 prediction. Accuracy captures only
arXiv:2609.00742v1 Announce Type: new Abstract: As AI video generators achieve cinematic realism, reliable detection becomes essential for safeguarding digital trust. We identify cross-scale coupling
arXiv:2609.01384v1 Announce Type: new Abstract: Long-duration outdoor coverage with autonomous platforms remains challenging beyond classical planning: deployments face localization drift in open spac
arXiv:2609.01232v1 Announce Type: cross Abstract: Vision Transformers (ViTs) are increasingly used in split-inference systems, where edge devices transmit intermediate token representations to a remot
arXiv:2609.01426v1 Announce Type: cross Abstract: Clear cell renal cell carcinoma (CCRCC) grading is essential for treatment planning, yet existing approaches either analyze patch-level images directl
arXiv:2609.01279v1 Announce Type: cross Abstract: Emotion is expressed in text along a wide spectrum, from surface lexical cues to inferences entangled with content. Most layer-wise analyses of emotio
arXiv:2609.00658v1 Announce Type: new Abstract: Metric questions about video require vision-language models to use supplied real-world references to convert visual measurements into physical units. Ye
arXiv:2609.01034v1 Announce Type: new Abstract: The central flow of Cohen et al. (2025) is an empirically accurate continuous-time model of gradient descent at the edge of stability in deep learning,
arXiv:2609.00597v1 Announce Type: new Abstract: With the rapid rise of large language models (LLMs), controlling undesirable model behaviors has become increasingly important. Existing behavioral cont
arXiv:2609.00470v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) grounds large language models in external corpora, but implicit trust in retrieved documents creates a critical att
arXiv:2609.00498v1 Announce Type: new Abstract: Jailbreak robustness has become central to large language model (LLM) safety evaluation, yet prevailing methodologies rely primarily on refusal behavior
arXiv:2505.13180v3 Announce Type: replace Abstract: Integrating Large Language Models with symbolic planners is a promising direction for obtaining verifiable and grounded plans, with recent works ext
arXiv:2608.28778v1 Announce Type: cross Abstract: Autonomous vehicles (AVs) rely on accurate camera-LiDAR calibration for multimodal sensor fusion. In practice, calibration can drift due to vibration,
arXiv:2608.29537v1 Announce Type: cross Abstract: Frozen vision-language-action (VLA) policies offer broad manipulation skills but execute open-loop action chunks without tracking task progress, so th
arXiv:2608.29355v1 Announce Type: new Abstract: Large non-uniform point sets make direct attention-based surrogate modeling costly for ship hydrodynamics. We introduce APPSolver, a point-wise flow-pre
arXiv:2608.29510v1 Announce Type: new Abstract: Aerial object detection is increasingly deployed in real-world applications, but models remain vulnerable to physical, universal adversarial patches tha
arXiv:2608.30536v1 Announce Type: new Abstract: Reliable execution of long-horizon mobile manipulation tasks remains challenging because overall task success depends on the successful completion of mu
arXiv:2608.29428v1 Announce Type: new Abstract: Single-trial EEG analyses are often organized around events and latencies, yet EEG-based reaction-time (RT) prediction is posed as scalar regression on
arXiv:2602.01695v2 Announce Type: replace Abstract: Latent reasoning reduces the token-generation cost of chain-of-thought reasoning by replacing explicit intermediate tokens with continuous latent tr
arXiv:2608.30398v1 Announce Type: new Abstract: In pointwise document reranking, Chain-of-Thought models typically underperform direct scoring models. While existing diagnostics attribute this to infe
arXiv:2608.29658v1 Announce Type: cross Abstract: Accurate traffic flow prediction is fundamental to intelligent transportation systems, playing a pivotal role in urban mobility optimization and smart
arXiv:2608.28681v1 Announce Type: new Abstract: Probability calibration aligns model confidence with predictive accuracy, enabling clinicians to identify unreliable segmentation regions. This alignmen
arXiv:2608.30295v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated strong capabilities in handling long-context tasks, but processing such long contexts remains challengi
arXiv:2608.29114v1 Announce Type: cross Abstract: Vision-and-Language Navigation (VLN) requires agents to reason over accumulated observations while continuously exploring unseen regions. However, exi
arXiv:2608.30337v1 Announce Type: new Abstract: Antimicrobial peptides (AMPs) often act against multiple pathogen classes, making multi-label activity prediction a more realistic screening target than
arXiv:2608.30442v1 Announce Type: new Abstract: Recent offline reinforcement learning (RL) studies report policies that outperform physician decisions on clinical outcomes. We conduct a systematic, pa
arXiv:2608.28896v1 Announce Type: new Abstract: Industrial process networks do not maintain a single effective topology while operating: streams are throttled or bypassed, and units move between idle,
arXiv:2608.29004v1 Announce Type: cross Abstract: The advances in visual information modeling and representation during the last decades are remarkable, mainly supported by Convolutional Neural Networ
arXiv:2608.30386v1 Announce Type: cross Abstract: Hybrid linear-attention architectures have recently scaled to large open-weight models, offering quality competitive with full attention while substan
arXiv:2608.31029v1 Announce Type: new Abstract: End-to-end autonomous driving models plan future trajectories from raw sensor input. While earlier driving benchmarks often measured deviation from the
arXiv:2608.29543v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have established conversational text-to-SQL as a practical interface between users and databases, ofte
arXiv:2608.28982v1 Announce Type: new Abstract: Physics-integrated 3D Gaussian representations make it possible to simulate image-reconstructed assets directly as particles, but current Gaussia-MPM pi
arXiv:2608.30804v1 Announce Type: new Abstract: Monitoring the health of heterogeneous industrial robot fleets is severely challenged by the multi-modal nature of their operational cycles and a persis
arXiv:2608.28692v1 Announce Type: new Abstract: In closed forests, neighboring tree crowns often stop short of touching, leaving a network of narrow gaps known as crown shyness. The pattern belongs to
If you build agent skills in production, check out this great paper from Alibaba. You can think of a production agent skill as a directory. The root loads on activation, and references, schemas, scrip
arXiv:2608.29612v1 Announce Type: new Abstract: Sustained scientific work requires a knowledge substrate that carries interpretation across tasks and preserves paths to source evidence. We call this p
arXiv:2502.10577v2 Announce Type: replace-cross Abstract: Instruct-based large language models (LLMs) have been shown to propagate and even amplify gender bias when prompted with contextually constrai
arXiv:2608.30487v1 Announce Type: cross Abstract: Deep networks trained on noisy labels simultaneously generalize on clean data and memorize flipped labels. These are usually conflated as pressures on
arXiv:2603.02482v2 Announce Type: replace-cross Abstract: Safety evaluation of multimodal large language models requires tracking not only whether an attack succeeds, but also how the interaction unfo
arXiv:2608.29943v1 Announce Type: cross Abstract: Large language models (LLMs) can memorize sensitive information, raising serious privacy concerns. Machine unlearning offers a potential solution to r
arXiv:2608.30760v1 Announce Type: new Abstract: Recent studies have shown that multimodal large language models (MLLMs) can serve as embodied agents, translating language instructions and visual obser
arXiv:2608.30388v1 Announce Type: cross Abstract: Cross-view video representation learning aims to capture viewpoint-invariant action semantics despite substantial appearance changes across egocentric
arXiv:2608.30946v1 Announce Type: new Abstract: Closed-loop human-AI systems generate high-dimensional behavioural trajectories whose collective dynamics remain obscure. Using 297,915 learners' adapti
arXiv:2603.18272v2 Announce Type: replace Abstract: While large language models (LLMs) have advanced the development of general-purpose agents, robust generalization to unseen tasks remains challengin
arXiv:2602.07837v4 Announce Type: replace Abstract: Online policy learning directly in the physical world is a promising yet challenging direction for embodied intelligence. Unlike simulation, real-wo