Knowledge catalogue
arXiv:2605.07146v1 Announce Type: new Abstract: Underwater salient object detection (USOD) plays a vital role in marine vision tasks but remains fundamentally challenging due to severe visual degradat
arXiv:2605.07048v1 Announce Type: cross Abstract: De novo molecular generation from tandem mass spectra is a challenging inverse problem whose core difficulty lies in the circular dependency between a
arXiv:2605.07395v1 Announce Type: cross Abstract: Efficient routing across multiple LLMs enables cost-quality tradeoffs by directing queries to the cheapest capable model. Prior work attributes routin
arXiv:2605.08070v1 Announce Type: new Abstract: A standard technique for scaling inference-time reasoning is Self-Consistency, whereby multiple candidate answers are sampled from an LLM and the most c
arXiv:2605.06094v2 Announce Type: replace-cross Abstract: Training VideoLLMs for complex reasoning remains challenging due to sparse sequence level rewards and the lack of fine grained credit assignme
arXiv:2605.06708v1 Announce Type: cross Abstract: Visual text compression (VTC) promises efficient long-context processing by rendering text into an image and re-encoding it with a vision-language mod
arXiv:2605.06175v2 Announce Type: replace Abstract: Vision-language-action (VLA) models inherit rich visual-semantic priors from pre-trained vision-language backbones, but adapting them to robotic con
arXiv:2605.06761v1 Announce Type: new Abstract: The web is complex, open-ended, and constantly changing, making it challenging to scale training data for visual web agents. Existing data collection at
arXiv:2605.06731v1 Announce Type: cross Abstract: Personalized LLM agents maintain persistent cross-session state to support long-horizon collaboration. Yet, this persistence introduces a subtle but c
arXiv:2605.07533v1 Announce Type: new Abstract: Large Language Models (LLMs) have recently demonstrated strong performance in machine translation (MT). However, most prior work focuses on improving or
arXiv:2605.07527v1 Announce Type: cross Abstract: Recent work has observed that explanations produced by Self-Interpretable Graph Neural Networks (SI-GNNs) can be self-inconsistent: when the model is
arXiv:2605.07068v1 Announce Type: cross Abstract: The LLM Wiki pattern, to compile and provide domain knowledge into a persistent artifact and serve it to LLMs via KV cache inference, promises context
arXiv:2605.07579v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) for Large Reasoning Models hinges on baseline estimation for variance reduction, but existing ap
ERNIE 5.1 is here 🚀 ERNIE 5.1 significantly reduces pretraining cost while compressing total parameters to ~1/3 and activated parameters to ~1/2 — using only ~6% of the pretraining cost compared to mo
Hot take on METR’s new graph that so many people are flipping about today. • Claude Code is a real advance; Mythos probably builds on some of what is learned there. But… • If you read the graph carefu
This is confused, but popular. Popular because it tells a bunch of people what they want to hear. Confused for a couple reasons: first, Mythos probably isn’t a pure LLM. (Claude Code isn’t, and it pro
Yann LeCun closed 1.03B for AMI Labs on March 10. Three days later, this paper dropped from his NYU collaborators. 15M parameters. Single GPU. A few hours of training. LeWorldModel is the first JEPA t
arXiv:2605.04916v1 Announce Type: cross Abstract: Inductive Logic Programming (ILP) learns interpretable logical rules from data. Existing methods are transductive: their learned parameters are bound
arXiv:2506.14432v3 Announce Type: replace-cross Abstract: We present FOMO260K, a large-scale, heterogeneous dataset of 260,927 brain Magnetic Resonance Imaging (MRI) scans from 77,589 MRI sessions and
arXiv:2605.04066v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) is an essential paradigm that enhances the reasoning capabilities of Large Language Models (LLMs).
arXiv:2605.04236v1 Announce Type: new Abstract: Large Language Model ensembles improve reasoning accuracy up to a performance boundary; beyond it, additional deliberation degrades accuracy. Static-bud
arXiv:2605.05123v1 Announce Type: new Abstract: In offline-to-online reinforcement learning (O2O-RL), policies are first safely trained offline using previously collected datasets and then further fin
arXiv:2602.13670v2 Announce Type: replace Abstract: Class-incremental learning (CIL) with pre-trained models (PTMs) faces a critical trade-off between efficient adaptation and long-term stability. Whi
arXiv:2605.05155v1 Announce Type: new Abstract: As 3D Gaussian Splatting (3DGS) gains attention in immersive media and digital content creation, assessing the aesthetics of 3D scenes becomes important
arXiv:2605.05000v1 Announce Type: cross Abstract: Windows Component Object Model (COM) services run with elevated privileges and are widely accessible to authenticated users, making race conditions in
arXiv:2605.04193v1 Announce Type: cross Abstract: Inductive Logic Programming (ILP) aims to learn interpretable first-order rules from data, but existing symbolic and neuro-symbolic approaches struggl
arXiv:2605.04541v1 Announce Type: new Abstract: Image-to-point-cloud registration (I2P) is a fundamental task in robotic applications such as manipulation,grasping, and localization. Existing deep lea
arXiv:2603.25956v2 Announce Type: replace Abstract: Time-series anomaly detection (TSAD) is a critical component in monitoring complex systems, yet modern deep learning-based detectors are often highl
arXiv:2603.00492v2 Announce Type: replace Abstract: Per-scene optimization methods such as 3D Gaussian Splatting provide state-of-the-art novel view synthesis quality but extrapolate poorly to under-o
arXiv:2605.04857v1 Announce Type: new Abstract: This paper presents the development and validation of an eye-tracking dataset designed to investigate how second-language (L2) learners process idiomati
arXiv:2605.04128v1 Announce Type: cross Abstract: We present JoyAI-Image, a unified multimodal foundation model for visual understanding, text-to-image generation, and instruction-guided image editing
arXiv:2602.19041v2 Announce Type: replace Abstract: A recurring challenge in preference fine-tuning (PFT) is handling extit{intransitive} (i.e., cyclic) preferences. Intransitive preferences often ste
arXiv:2605.04077v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a central paradigm for improving reasoning and code generation in large language mode
arXiv:2605.05121v1 Announce Type: new Abstract: Automated mental health prediction using textual data has shown promising results with deep learning and large language models. However, deploying these
arXiv:2605.04793v1 Announce Type: new Abstract: Koopman-based neural MPC models generate time-varying dynamics from historical data, but preserve convexity by enforcing that the system operator is ind
arXiv:2605.04641v1 Announce Type: new Abstract: Although Large Vision-Language Models (LVLMs) have demonstrated remarkable performance on downstream tasks, they frequently produce contents that deviat
arXiv:2605.04652v1 Announce Type: new Abstract: Temporal knowledge graph (TKG) reasoning aims to predict future events from historical facts. A key challenge lies in jointly capturing two sources of p
arXiv:2605.04206v1 Announce Type: new Abstract: Large-scale restoration in drylands is widely promoted to address land degradation and biodiversity loss, yet many efforts rely on long-term irrigation,
arXiv:2502.10148v3 Announce Type: replace Abstract: Cooperative multi-agent reinforcement learning (MARL) struggles with sample efficiency, interpretability, and generalization. While Large Language M
arXiv:2605.04366v1 Announce Type: cross Abstract: Safety-critical scenarios are essential for the development of autonomous vehicles (AVs) but are rare in real-world driving data. While simulation off
arXiv:2605.05126v1 Announce Type: new Abstract: Current Vision-Language-Action (VLA) models primarily focus on mapping 2D observations to actions, but exhibit notable limitations in spatiotemporal per
arXiv:2605.04185v1 Announce Type: new Abstract: When deploying reinforcement learning policies to physical robots, actuator rate constraints -- hard limits on how fast each joint can move per control
arXiv:2605.04059v1 Announce Type: cross Abstract: Deep learning models continue to scale, with some requiring more storage than many large-scale datasets. Thus, we introduce a new paradigm: Continual
arXiv:2605.04346v1 Announce Type: cross Abstract: The Forward-Forward algorithm eliminates global gradient flow and full network activations storage. However, in convolutional settings, existing BP-fr
arXiv:2605.05136v1 Announce Type: new Abstract: Domain Generalization (DG) aims to learn representations that remain robust under out-of-distribution (OOD) shifts and generalize effectively to unseen
arXiv:2605.04477v1 Announce Type: new Abstract: Online reinforcement learning from human feedback (RLHF) has emerged as a promising paradigm for aligning large language models (LLMs) by continuously c
arXiv:2605.02970v1 Announce Type: cross Abstract: Network traffic anomaly detection represents a critical cybersecurity task, yet widespread encryption makes this task increasingly challenging. In res
arXiv:2605.04198v1 Announce Type: new Abstract: Performance of deep learning models is strongly governed by architectural capacity, with width and depth as primary controls. However, in physical-scien
arXiv:2605.04324v1 Announce Type: new Abstract: Decentralized multi-source domain adaptation seeks to transfer knowledge from multiple heterogeneous and related source domains to an unlabeled target d
arXiv:2605.04405v1 Announce Type: new Abstract: Driven by the rapid development of generative AI models, deepfake detectors are compelled to undergo periodic recalibration to capture newly developed s
arXiv:2605.05054v1 Announce Type: new Abstract: Recent flow matching (FM) methods improve the few-shot adaptation of vision-language models, by modeling cross-modal alignment as a continuous multi-ste
arXiv:2404.13649v2 Announce Type: replace-cross Abstract: Dimension reduction techniques usually lose information in the sense that reconstructed data are not identical to the original data. However,
arXiv:2603.26114v2 Announce Type: replace Abstract: DPD-Cancer is a graph-attention deep learning framework for predicting small-molecule DPD-Cancer is a graph-attention deep learning framework for pr
arXiv:2605.05092v1 Announce Type: cross Abstract: Safe L2/L3 driving automation requires anticipating human-in-the-loop reactions during shared-control transitions. While most driving world models for
arXiv:2601.19690v2 Announce Type: replace Abstract: Vision Mamba models have been extensively researched in various fields, which address the limitations of previous models by effectively managing lon
arXiv:2605.04997v1 Announce Type: new Abstract: DualTCN is the first deep-learning framework for inverting time-domain marine controlled-source electromagnetic (MCSEM) transient data. Moving away from
arXiv:2605.04255v1 Announce Type: cross Abstract: Many machine learning problems involve data supported on curved spaces such as spheres, rotation groups, hyperbolic spaces, and general Riemannian man
arXiv:2605.04960v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR), particularly Group Relative Policy Optimization (GRPO), has advanced LLM reasoning. However, GRPO
arXiv:2605.04719v1 Announce Type: new Abstract: Tool-integrated Text-to-SQL parsing has emerged as a promising paradigm, framing SQL generation as a sequential decision-making process interleaved with
arXiv:2605.04651v1 Announce Type: cross Abstract: Adapting pretrained models typically involves a trade-off between the high training costs of backpropagation and the heavy inference overhead of memor