Knowledge catalogue
arXiv:2310.15676v2 Announce Type: replace-cross Abstract: Multi-modal 3D Intelligence has gained considerable attention due to its wide applications in autonomous driving and world simulation, etc. Co
arXiv:2606.01351v1 Announce Type: new Abstract: The transition from single-turn models to Multi-Agent Systems (MAS) promises enhanced problem-solving capabilities, yet the centralized orchestration to
arXiv:2601.22947v2 Announce Type: replace Abstract: Masked diffusion language models (MDLMs) generate text by unmasking tokens in parallel and have recently emerged as alternatives to autoregressive l
arXiv:2506.11083v3 Announce Type: replace Abstract: We introduce RedDebate, a novel multi-agent debate framework that provides the foundation for Large Language Models (LLMs) to identify and mitigate
arXiv:2505.18877v4 Announce Type: replace Abstract: Low-Rank Adaptation (LoRA) lowers the computational and memory overhead of fine-tuning large models by updating a low-dimensional subspace of the pr
arXiv:2606.00680v1 Announce Type: new Abstract: Offline reinforcement learning (RL) aims to optimize policies from pre-collected datasets. A bottleneck of this paradigm is managing epistemic uncertain
arXiv:2511.06720v3 Announce Type: replace Abstract: Out-of-distribution (OOD) detection is a critical requirement for reliable autonomous driving, where safety depends on recognizing road obstacles an
arXiv:2606.02326v1 Announce Type: new Abstract: Hard constraints are usually treated as terminal vetoes: once a candidate violates a requirement, the learned rule rejects it and any repair is handled
arXiv:2606.01911v1 Announce Type: new Abstract: Visual Autoregressive (AR) models generate images by predicting discrete tokens that are decoded by a visual tokenizer. Despite demonstrating strong ove
arXiv:2602.07083v2 Announce Type: replace-cross Abstract: Structural modeling is a fundamental component of computational engineering science, in which even minor physical inconsistencies or specifica
arXiv:2606.00306v1 Announce Type: cross Abstract: Reverse Kullback-Leibler (RKL) divergence is widely favored over forward KL (FKL) in large language models (LLM) distillation, yet this preference is
arXiv:2606.00559v1 Announce Type: cross Abstract: Neural algorithmic reasoning has emerged as a popular research direction. It aims to train neural networks to mimic the step-by-step behavior of class
arXiv:2606.02277v1 Announce Type: new Abstract: Vision-language-action (VLA) models are built on the premise that semantic understanding from pretrained language or vision-language backbones should gu
arXiv:2601.18115v2 Announce Type: replace Abstract: We study the problem of learning a single neuron under standard squared loss in the presence of arbitrary label noise and group-level distributional
arXiv:2606.00628v1 Announce Type: new Abstract: Self-distillation improves learning efficiency by rewriting reference answers as training data that better matches the model's own distribution. However
arXiv:2606.00341v1 Announce Type: cross Abstract: As AI agents are increasingly deployed in real personal and corporate settings (email accounts, development workflows, company databases, etc.), safet
arXiv:2606.01689v1 Announce Type: cross Abstract: The detection and segmentation of infrared small targets have important application significance in the fields of surveillance and security, maritime
arXiv:2602.20807v2 Announce Type: replace Abstract: Combining 3D Gaussian splatting with Simultaneous Localization and Mapping (SLAM) has gained popularity as it enables continuous 3D environment reco
arXiv:2511.17502v3 Announce Type: replace Abstract: We introduce RynnVLA-002, a unified Vision-Language-Action (VLA) and world model. The world model leverages action and visual inputs to predict futu
arXiv:2606.00808v1 Announce Type: new Abstract: Source-free graph domain adaptation (SF-GDA) aims to adapt source-trained graph models to unlabeled target graphs when source graphs are no longer acces
arXiv:2512.02342v3 Announce Type: replace-cross Abstract: The stochastic Polyak step size (SPS) has proven to be a promising choice for stochastic gradient descent (SGD), delivering competitive perfor
arXiv:2503.11832v5 Announce Type: replace Abstract: Recent vision language models (VLMs) have made remarkable strides in generative modeling with multimodal inputs, particularly text and images. Howev
arXiv:2606.00460v1 Announce Type: new Abstract: Speech-aware large language models often generalize poorly to out-of-domain settings. We propose SALSA (Speech-Aware LLM Adaptation via Learned Steering
arXiv:2503.24183v3 Announce Type: replace Abstract: The expansion of ride-sourcing services such as Uber and Lyft has reshaped urban transportation by offering flexible, on-demand mobility via mobile
arXiv:2606.01316v1 Announce Type: new Abstract: Scientific discovery demands intelligence, perseverance, and serendipity across vast search spaces. Today, top scientific capabilities remain siloed--on
arXiv:2606.00377v1 Announce Type: new Abstract: Diffusion models have emerged as the backbone of modern generative AI, powering advances in vision, language, audio and other modalities. Despite their
arXiv:2510.08825v2 Announce Type: replace Abstract: Large language models (LLMs) augmented with knowledge graphs (KGs) offer a promising approach for knowledge-intensive reasoning. Central to this app
arXiv:2503.06520v3 Announce Type: replace Abstract: Traditional methods for reasoning segmentation rely on supervised fine-tuning with categorical labels and simple descriptions, limiting its out-of-d
arXiv:2606.01416v1 Announce Type: new Abstract: Tool-augmented large language model (LLM) agents rely on orchestration layers that coordinate planning, retrieval, tool invocation, validation, memory,
arXiv:2601.22965v2 Announce Type: replace Abstract: Diffusion policies (DP) have demonstrated significant potential in visual navigation by capturing diverse multi-modal trajectory distributions. Howe
arXiv:2606.01525v1 Announce Type: new Abstract: Semi-supervised hierarchical clustering aims to learn a tree structure consistent with data patterns and user-provided supervision. Supervision is usual
arXiv:2512.00088v2 Announce Type: replace Abstract: We propose SemImage, a novel method for representing a text document as a two-dimensional semantic image to be processed by convolutional neural net
arXiv:2606.00021v1 Announce Type: cross Abstract: Speculative Decoding (SD) accelerates Large Language Model (LLM) inference by employing a lightweight draft model to propose candidate tokens, which a
arXiv:2606.00732v1 Announce Type: new Abstract: Learning long-range non-stationary temporal patterns remains a core challenge for modern sequence models, particularly in strict streaming settings. In
arXiv:2606.01723v1 Announce Type: cross Abstract: Real-world regression often exhibits shortcuts: attributes that are spuriously correlated with continuous targets in training, yet unreliable under de
arXiv:2606.00090v1 Announce Type: cross Abstract: Physical AI systems increasingly map multimodal observations, language instructions, and learned world representations into physically consequential a
arXiv:2603.11653v2 Announce Type: replace Abstract: Continual Reinforcement Learning (CRL) for Vision-Language-Action (VLA) models is a promising direction toward self-improving embodied agents that c
arXiv:2606.02544v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) have recently emerged as a promising alternative to autoregressive (AR) LLMs, offering faster inference throug
arXiv:2503.05641v4 Announce Type: replace-cross Abstract: Combining existing pre-trained LLMs is a promising approach for diverse reasoning tasks. However, task-level expert selection is often too coa
arXiv:2606.00822v1 Announce Type: cross Abstract: Skill-based LLM agents increasingly rely on long procedural documents, but full-document prompting wastes tokens and dilutes information critical to e
arXiv:2606.01139v1 Announce Type: new Abstract: Agent skills are procedural artifacts that enable LLM agents to execute workflows, verify constraints, and recover from failures. Existing self-evolving
arXiv:2606.01314v1 Announce Type: new Abstract: Recent self-evolving agents have shown that skills can be discovered, refined, and accumulated through execution. However, existing skill-evolution fram
arXiv:2603.08000v2 Announce Type: replace Abstract: Large reasoning models (LRMs) like OpenAI o1 and DeepSeek-R1 achieve high accuracy on complex tasks by adopting long chain-of-thought (CoT) reasonin
arXiv:2606.01101v1 Announce Type: cross Abstract: The quadratic complexity of self-attention remains a bottleneck for Large Language Models (LLMs) processing ultra-long contexts. The Naive Bayes Cogni
arXiv:2512.04069v2 Announce Type: replace Abstract: Vision Language Models (VLMs) demonstrate strong qualitative visual understanding, but struggle with metrically precise spatial reasoning required f
arXiv:2606.00572v1 Announce Type: new Abstract: Passenger count data from public transit systems reveals urban mobility patterns and is essential for planning, operation, and optimisation. However, no
arXiv:2606.02427v1 Announce Type: cross Abstract: Existing evaluations of neural operators and in-context operator learning rely primarily on prediction error, but accurate output prediction does not
arXiv:2512.00062v2 Announce Type: replace-cross Abstract: Robotic policy learning for complex real-world manipulation tasks has seen rapid recent progress, enabled in large part by the ability to coll
arXiv:2301.06308v2 Announce Type: replace-cross Abstract: Sharpness-aware minimization (SAM) is a training method that seeks to find flat minima in deep learning, resulting in state-of-the-art perform
arXiv:2603.00963v2 Announce Type: replace-cross Abstract: While reinforcement learning (RL) has been central to the recent success of large language models (LLMs), RL optimization is notoriously unsta
arXiv:2606.01790v1 Announce Type: cross Abstract: Vision-language-model-based graphical user interface (GUI) agents have shown broad automation capabilities, yet deployment is bottlenecked by a key-va
// State-Externalizing Harnesses // A new paradigm is emerging on how to effectively build agents and harnesses. If there is a state that the environment can maintain reliably, it probably doesn't bel
arXiv:2410.02511v2 Announce Type: replace Abstract: With expansive state-action spaces, efficient multi-agent exploration remains a longstanding challenge in reinforcement learning. Although pursuing
arXiv:2602.06925v2 Announce Type: replace Abstract: Autonomous drone racing pushes the boundaries of high-speed motion planning and multi-agent strategic decision-making. Success in this domain requir
arXiv:2510.09608v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) could power real-time assistants and autonomous agents, but they face a critical challenge: understanding near-i
arXiv:2606.01843v1 Announce Type: cross Abstract: Deepfake detection suffers from poor generalization across forgery methods, as existing models tend to rely on spurious method-specific shortcuts that
arXiv:2602.23866v2 Announce Type: replace-cross Abstract: Software engineering agents (SWE) are improving rapidly, with recent gains largely driven by reinforcement learning (RL). However, RL training
arXiv:2510.23379v2 Announce Type: replace-cross Abstract: We investigate a relatively under-explored class of hybrid neurosymbolic models that integrate symbolic learning with neural reasoning to cons
arXiv:2606.02219v1 Announce Type: new Abstract: Object pose estimation is a fundamental problem for an agent system to perceive or manipulate objects in images or videos. However, current instance-lev
arXiv:2504.04718v2 Announce Type: replace-cross Abstract: Recent studies have demonstrated that test-time compute scaling effectively improves the performance of small language models (sLMs). However,