Knowledge catalogue
arXiv:2605.19717v1 Announce Type: new Abstract: Large Language Models (LLMs) can generate Computer-Aided Design (CAD), yet lack physical comprehension required for reliable engineering design. Instead
arXiv:2605.20185v1 Announce Type: cross Abstract: Existing Gaussian avatar methods typically parameterize geometry on a body-template surface, which entangles the avatar's representation space with th
arXiv:2511.06943v3 Announce Type: replace-cross Abstract: Global plant maps of plant traits, such as leaf nitrogen or plant height, are essential for understanding ecosystem processes, including the c
arXiv:2605.19623v1 Announce Type: new Abstract: Segmenting images is critical for visual understanding but demands extensive pixel-level annotations. Foundational models have enabled new paradigms for
arXiv:2605.18832v1 Announce Type: cross Abstract: The Transformer is the foundational building block of modern AI, yet offers no principled handling of uncertainty, which is prevalent in real applicat
arXiv:2605.19257v1 Announce Type: new Abstract: Monocular SLAM historically suffers from scale ambiguity and tracking failure in dynamic environments. While recent vision foundation models (VFMs) prov
arXiv:2605.19943v1 Announce Type: new Abstract: Tiny Recursive Models (TRM) solve complex reasoning tasks with a fraction of the parameters of modern large language models (LLMs) by iteratively refini
arXiv:2605.20079v1 Announce Type: cross Abstract: Diffusion and flow-based generative models dominate visual synthesis, with guidance aligning samples to user input and improving perceptual quality. H
arXiv:2602.04883v2 Announce Type: replace-cross Abstract: We present protein autoregressive modeling (PAR), the first multi-scale autoregressive framework for protein backbone generation via coarse-to
arXiv:2605.19549v1 Announce Type: cross Abstract: Deep neural networks (DNNs) are suffering from ethical issues such as individual discrimination. In response, extensive NN repair techniques have been
arXiv:2605.19329v1 Announce Type: cross Abstract: Conventional vision-language models (VLMs) struggle to interpret scenes captured under adverse conditions (e.g., low light, high dynamic range, or fas
arXiv:2605.18799v1 Announce Type: cross Abstract: Large language models can fail in critic interaction not only by answering incorrectly, but also by abandoning an initially correct scientific solutio
arXiv:2602.04663v2 Announce Type: replace-cross Abstract: Reinforcement learning has been widely applied to diffusion and flow models for visual tasks such as text-to-image generation. However, these
arXiv:2407.13193v4 Announce Type: replace Abstract: Large language models (LLMs) have achieved strong empirical performance in various fields, benefiting from their huge amount of parameters that stor
arXiv:2605.19344v1 Announce Type: new Abstract: Linguistic cues such as 'I believe' and 'probably' offer an intuitive interface for communicating confidence, yet a generalisable, principled calibratio
arXiv:2605.20061v1 Announce Type: new Abstract: Reinforcement learning from verifiable rewards (RLVR) is a promising paradigm for improving large language model (LLM) agents on long-horizon interactiv
arXiv:2510.14261v2 Announce Type: replace Abstract: We present an experimental recipe for studying the relationship between training data and language model (LM) behavior. We outline steps for interve
arXiv:2412.02818v4 Announce Type: replace-cross Abstract: Robot manipulation policies, while central to the promise of physical AI, are highly vulnerable in the presence of external variations in the
arXiv:2604.07303v2 Announce Type: replace Abstract: Understanding and modeling animal behavior is essential for studying collective motion, decision-making, and bio-inspired robotics. Yet, evaluating
arXiv:2605.18852v1 Announce Type: cross Abstract: Checkpoint selection for multimodal large language models (MLLMs) presents significant challenges when performance differentials are marginal and eval
arXiv:2605.18864v1 Announce Type: cross Abstract: Recent studies observe that reinforcement learning with verifiable rewards (RLVR) reliably improves pass@1 on reasoning tasks, yet often fails to yiel
arXiv:2605.19095v1 Announce Type: cross Abstract: Schedule-Free Learning has shown promise as a practical anytime training method for machine learning, showing success across dozens of standard benchm
arXiv:2510.18821v3 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) has become the mainstream technique for training LLM agents. However, RLVR highly depends on w
arXiv:2605.19340v1 Announce Type: new Abstract: Vision foundation models (VFMs) have achieved strong performance across various vision tasks. However, it still remains challenging to apply VFMs for cr
arXiv:2510.05431v4 Announce Type: replace Abstract: Organizing large-scale patent corpora according to classification schemes is a core information management task that determines the accuracy and eff
arXiv:2605.19342v1 Announce Type: new Abstract: Multimodal latent-space reasoning aims to replace explicit thinking with images by performing visual reasoning directly in a compact latent space. Howev
arXiv:2605.18971v1 Announce Type: cross Abstract: What determines the quality of a tabular foundation model? Unlike language or vision, tabular foundation models acquire their inductive biases almost
arXiv:2605.19823v1 Announce Type: cross Abstract: Neural operators have achieved strong performance in learning solution operators of partial differential equations (PDEs), but their inherently contin
arXiv:2602.17001v2 Announce Type: replace Abstract: Natural Language Querying for Time Series Databases (NLQ4TSDB) aims to assist non-expert users retrieve meaningful events, intervals, and summaries
arXiv:2605.18836v1 Announce Type: cross Abstract: Dataset Distillation (DD) synthesizes a compact synthetic dataset that preserves the training utility of a full dataset. However, its standard formula
arXiv:2605.18905v1 Announce Type: cross Abstract: Neural operators have emerged as a powerful, discretization-invariant framework for solving partial differential equations (PDEs). Although establishe
arXiv:2605.19856v1 Announce Type: cross Abstract: Training very deep neural networks requires controlling the propagation of magnitudes across depth. Without such control, activations and gradients ma
arXiv:2605.19338v1 Announce Type: cross Abstract: Frontier AI models and multi-agent systems have led to significant improvements in mathematical reasoning. However, for problems requiring extended, l
arXiv:2605.18765v1 Announce Type: cross Abstract: To augment Large Language Models (LLMs) for multi-hop question answering, a mainstream solution within Graph Retrieval Augmented Generation (GraphRAG)
arXiv:2605.19895v1 Announce Type: new Abstract: Constraint programming practitioners accelerate hard problems through a layered set of techniques applied in order of risk. Standard hardening (symmetry
arXiv:2605.18851v1 Announce Type: new Abstract: Recent advances in Reinforcement Learning (RL) have underscored its potential for incentivizing reasoning capabilities of Large Language Models (LLMs).
arXiv:2605.18920v1 Announce Type: cross Abstract: Generative Recommendation (GR) has emerged as a promising paradigm by formulating item recommendation as a sequence-to-sequence generation task over i
arXiv:2605.18979v1 Announce Type: new Abstract: We propose Tabular Q-Learning (TabQL), a reinforcement learning framework that replaces the conventional parametric Q-network in Deep Q-Learning (DQN) w
arXiv:2602.11910v2 Announce Type: replace-cross Abstract: Audio diffusion models can synthesize high-fidelity music from text, yet achieving fine-grained control over specific musical attributes remai
arXiv:2605.20068v1 Announce Type: cross Abstract: Standard generative models struggle with heavy-tailed data: Lipschitz architectures cannot produce power-law tails from Gaussian noise, and interpolat
arXiv:2603.29501v2 Announce Type: replace-cross Abstract: Many value-based deep reinforcement learning algorithms rely on target networks - lagged copies of the online network - to stabilize training.
arXiv:2605.19446v1 Announce Type: cross Abstract: Recently, pre-trained encoders have gained widespread use due to their strong capability in representation extraction. However, they are vulnerable to
arXiv:2605.18840v1 Announce Type: cross Abstract: Leaderboards rank frontier models on independent axes but do not reveal whether capabilities reinforce or trade off across releases -- and at the fron
arXiv:2605.18800v1 Announce Type: cross Abstract: Post-training quantization has emerged as a widely adopted technique for compressing and accelerating the inference of Large Language Models (LLMs). T
arXiv:2605.19196v1 Announce Type: new Abstract: Deep research agents increasingly automate complex information-seeking tasks, producing evidence-grounded reports via multi-step reasoning, tool use, an
arXiv:2512.18552v2 Announce Type: replace-cross Abstract: While current software agents powered by large language models (LLMs) and agentic reinforcement learning (RL) can boost programmer productivit
arXiv:2605.18792v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) improves large language models (LLMs) by incorporating external evidence, but it also introduces knowledge confli
arXiv:2605.19409v1 Announce Type: cross Abstract: Continual Model Merging (CMM) enables rapid customization of foundation models across sequentially arriving tasks, offering a scalable alternative to
Editor’s note: Urban Outfitters, Inc. (URBN) recently completed a major infrastructure upgrade, migrating its IBM Sterling Order Management System (Sterling OMS) from an Oracle database to Google Clou
arXiv:2605.19343v1 Announce Type: new Abstract: Single-cell perturbation modeling is fundamental for understanding and predicting cellular responses to genetic perturbations. However, existing approac
arXiv:2605.16795v1 Announce Type: cross Abstract: Video generative models have made remarkable progress, yet they often yield visual artifacts that violate grounding in physical dynamics. Recent works
arXiv:2605.18074v1 Announce Type: new Abstract: We present 4DLidarOpen, a large-scale open multi-modal dataset for autonomous driving, centered on 4D frequency-modulated continuous-wave (FMCW) Lidar s
arXiv:2605.17275v1 Announce Type: cross Abstract: Accurate forecasting of the Volatility-Covariance Matrix (VCV) is central to regulatory capital adequacy processes such as the Internal Capital Adequa
arXiv:2605.17954v1 Announce Type: cross Abstract: Modern multimodal large language models (MLLMs) typically keep the language model fixed and train a visual projector that maps the pixels into a seque
arXiv:2605.17131v1 Announce Type: cross Abstract: Point cloud stands as the most widely adopted format for representing 3D shapes and scenes due to its simplicity and geometric fidelity. However, its
arXiv:2605.17808v1 Announce Type: new Abstract: We develop a unified theoretical framework for data-free one-step sampling from unnormalized target distributions based on Wasserstein gradient flows. F
arXiv:2504.14820v2 Announce Type: replace Abstract: For peg-in-hole tasks, humans rely on binocular visual perception to locate the peg above the hole surface and then proceed with insertion. This pap
arXiv:2605.16299v1 Announce Type: cross Abstract: Large Language Models (LLMs) excel at code generation but remain heavily reliant on large-scale annotated solutions and verification-based supervision
arXiv:2503.12181v4 Announce Type: replace Abstract: Online planning in continuous state, action, and observation spaces remains challenging for autonomous systems. While Monte Carlo Tree Search (MCTS)
arXiv:2510.04309v3 Announce Type: replace Abstract: Controlling the behaviors of large language models (LLM) is fundamental to their safety alignment and reliable deployment. However, existing steerin