Knowledge catalogue
arXiv:2606.00880v1 Announce Type: cross Abstract: Continual reinforcement learning aims to produce agents that learn not only to improve at their current tasks but also to adapt as task distributions
arXiv:2606.00029v1 Announce Type: cross Abstract: Retrieval-augmented generation systems struggle with temporal reasoning and evidence fusion when answering complex questions over historical criminal
arXiv:2606.01213v1 Announce Type: cross Abstract: Despite tremendous recent progress, current text-guided image editing methods still struggle with many aspects of editing involving instruction follow
arXiv:2606.01031v1 Announce Type: cross Abstract: Audio-driven talking-head generation has advanced rapidly, yet existing evaluation protocols mainly rely on frame-wise metrics that assume strict temp
arXiv:2605.24470v2 Announce Type: replace Abstract: Video-text retrieval has witnessed remarkable progress driven by large-scale vision-language pretraining, yet most existing approaches inherit an im
arXiv:2606.00674v1 Announce Type: cross Abstract: Large Language Models (LLMs) aligned via outcome-based Reinforcement Learning (RL) frequently exhibit a critical failure mode: they achieve high perfo
arXiv:2605.05427v2 Announce Type: replace Abstract: Refusal rates are a poor proxy for LLM safety, i.e., a model may over-refuse benign prompts while still complying with harmful ones. We audit both f
arXiv:2510.10943v2 Announce Type: replace-cross Abstract: Bias in large language models (LLMs) remains a persistent challenge, often leading to stereotyping and unfair treatment across social groups.
🌞This is big Local AI news! A new open-source Computer-Use LLM has just launched. Holo 3.1 is H Company’s (🇫🇷) new local computer-use agent model that beats Qwen3.5-397B, Kimi-K2.5, and Sonnet 4.6! Si
arXiv:2606.02058v1 Announce Type: new Abstract: Event cameras emit asynchronous events in response to environmental appearance changes. The scarcity of real-world event datasets makes simulation essen
arXiv:2606.01169v1 Announce Type: cross Abstract: Spacecraft collision avoidance for low-thrust satellites often requires determining not only how to maneuver, but also how late a maneuver can begin w
arXiv:2606.01591v1 Announce Type: new Abstract: The TimeLogic Challenge evaluates formal temporal-logic reasoning over video - 16 operators (before, after, until, since, always, co-occur, ordering, ..
arXiv:2606.01540v1 Announce Type: cross Abstract: Shapley values are a widely used tool for attributing importance and interactions among input variables in black-box models, but their computation inv
arXiv:2602.07883v3 Announce Type: replace Abstract: LLM-powered agentic systems excel at complex long-horizon tasks, but remain constrained by static configurations fixed before execution. Such rigidi
arXiv:2606.00596v1 Announce Type: new Abstract: Large language models have rapidly evolved in multilingual competence and reasoning capacity, enabling their integration into Social Sciences and Humani
arXiv:2606.02000v1 Announce Type: cross Abstract: Diffusion models have shown remarkable success in video generation. However, whether such models are truly aware of the 3D structure underlying visual
arXiv:2602.13602v2 Announce Type: replace Abstract: We present revise (nderline{Re}asoning with nderline{Vi}deo nderline{S}parsity), a multi-round agent for video question answering (VQA). Instead of
arXiv:2410.09737v2 Announce Type: replace Abstract: A popular way to improve the expressive power of graph neural networks (GNNs) is to use Laplacian eigenvectors as additional node features, since th
arXiv:2606.00959v1 Announce Type: new Abstract: Understanding modality interaction in multimodal large language models (MLLMs) is central to reliable deployment. We introduce Partial Information Decom
arXiv:2606.01238v1 Announce Type: cross Abstract: While diffusion-based policies have impressive performance and expressivity, their long offline training slows down the data collection and policy dep
arXiv:2606.01967v1 Announce Type: new Abstract: While prompt engineering is instrumental in maximizing the capabilities of Large Language Models (LLMs) during inference, the role of prompts during tra
arXiv:2602.12724v3 Announce Type: replace Abstract: This study introduces TRANS: Terrain-aware Reinforcement learning for Agile Navigation under Social interactions, a deep reinforcement learning (DRL
arXiv:2606.01457v1 Announce Type: new Abstract: Bayesian optimization is a popular way to optimize expensive systems, where every experiment, simulation, or intervention costs time or money. In its st
arXiv:2304.11127v5 Announce Type: replace-cross Abstract: Recent scientific advances require complex experiment design, necessitating the meticulous tuning of many experiment parameters. Tree-structur
arXiv:2606.01755v1 Announce Type: new Abstract: Personalized large language models adapt responses to users' preferences and social attributes, but can introduce substantial universal truth inconsiste
arXiv:2606.01033v1 Announce Type: new Abstract: When a language model hallucinates, the final answer is wrong, but the mistake is not necessarily invisible inside the model. Different internal pathway
arXiv:2606.01599v1 Announce Type: new Abstract: Reinforcement learning (RL) for visual reasoning needs scalable, verifiable, and controllable training signals. Existing visual RL post-training trains
arXiv:2606.01249v1 Announce Type: cross Abstract: On-Policy Distillation (OPD) is a fundamental technique for efficient post-training of large language models (LLMs), with broad applications in agent
arXiv:2507.02983v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) hold significant promise for transforming digital health by enabling automated medical question answering. Howeve
arXiv:2606.01379v1 Announce Type: new Abstract: While prompt-based parameter-efficient continual learning mitigates catastrophic forgetting by isolating task-specific prompts, this isolation also limi
arXiv:2606.01595v1 Announce Type: new Abstract: Bayesian inference provides a principled framework for modeling epistemic uncertainty in neural networks by treating predictions as distributions rather
arXiv:2606.01694v1 Announce Type: cross Abstract: Thermal pedestrian MOT remains challenging because weak appearance cues and frequent detection interruptions cause severe trajectory fragmentation. We
arXiv:2606.01394v1 Announce Type: new Abstract: Systematic characterization of drug-disease relationships is essential for drug discovery and repurposing, yet is hindered by the heterogeneity and rapi
arXiv:2606.02304v1 Announce Type: new Abstract: LLM-based agents can solve multi-step interactive tasks by combining reasoning with environment feedback, yet each episode starts from the same fixed co
arXiv:2606.00351v1 Announce Type: new Abstract: Personalized visual understanding has advanced significantly, yet existing approaches struggle to localize and extract specific concepts when input imag
arXiv:2603.14010v2 Announce Type: replace Abstract: Articulated objects are fundamental for robotics, simulation of physics, and interactive virtual environments. However, recovering them from visual
arXiv:2606.00508v1 Announce Type: cross Abstract: This study introduces an intriguing phenomenon in Video LLMs: rather than merely translating frames into textual embeddings, Video LLMs establish a co
arXiv:2606.00119v1 Announce Type: cross Abstract: Reliable work zone mapping is important for connected and autonomous vehicles (CAVs) to navigate safely and smoothly through work zone areas. Cone-mou
arXiv:2510.07650v4 Announce Type: replace-cross Abstract: While most reinforcement learning methods today flatten the distribution of future returns to a single scalar value, distributional RL methods
arXiv:2606.00384v1 Announce Type: new Abstract: Fitting quantitative models to data is a central step in scientific workflows, yet it remains one of the least automated. Recent agent-based systems lev
arXiv:2606.00704v1 Announce Type: new Abstract: Real-world image super-resolution (Real-ISR) requires balancing structural fidelity to degraded observations with realistic detail synthesis. However, e
arXiv:2601.03309v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models, which integrate pretrained large Vision-Language Models (VLM) into their policy backbone, are gaining sig
arXiv:2606.02564v1 Announce Type: new Abstract: The recent 'Reasoning with Video' paradigm utilizes Video Generation Models (VGMs) to generate temporally coherent visual trajectories to complete reaso
arXiv:2606.00424v1 Announce Type: new Abstract: As large language models become stronger, weak supervisors may fail to provide reliable labels, preferences, or final judgments for complex outputs, lim
arXiv:2606.02096v1 Announce Type: new Abstract: Dynamic scene reconstruction from monocular videos remains highly challenging, as existing methods often struggle to balance global structural coherence
arXiv:2606.00046v1 Announce Type: cross Abstract: Video platforms such as YouTube have reshaped how users engage with entertainment and information, emphasizing brief, highly engaging content such as
arXiv:2606.02245v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) typically assumes that external knowledge is free, but many high-quality sources are paywalled, licensed, restricte
arXiv:2606.00262v1 Announce Type: cross Abstract: InfoNCE is the standard contrastive learning objective, but its softmax form is not only a computational convenience: it also encodes a statistical as
arXiv:2606.01247v1 Announce Type: new Abstract: Humans can reproduce the viewpoint specified by a target image through active head and body motion, yet spatial intelligence in foundation models has la
arXiv:2606.02526v1 Announce Type: cross Abstract: Long-tailed recognition poses a significant challenge for deep learning. The two-stage decoupling paradigm, which separates representation learning fr
arXiv:2602.10056v2 Announce Type: replace Abstract: We introduce WildCat, a high-accuracy, low-cost approach to compressing the attention mechanism in neural networks. While attention is a staple of m
arXiv:2606.00133v1 Announce Type: new Abstract: World models, internal simulators that learn the structure and dynamics of an environment, have emerged as a central paradigm in the pursuit of artifici
arXiv:2606.00113v1 Announce Type: new Abstract: Robotic manipulation depends on the ability to anticipate how actions reshape objects, contacts, and scene geometry before execution. Learned world mode
arXiv:2606.00390v1 Announce Type: cross Abstract: We present Zamba2-VL, a suite of vision-language models built on Zamba2, a hybrid language-model architecture combining Mamba2 state-space layers with
arXiv:2602.01962v2 Announce Type: replace-cross Abstract: Off-policy learning methods seek to derive an optimal policy directly from a fixed dataset of prior interactions. This objective presents sign
arXiv:2603.07751v2 Announce Type: replace-cross Abstract: Current Large Language Models have achieved Olympiad-level logic, yet Vision-Language Models paradoxically falter on elementary spatial tasks
arXiv:2602.07928v2 Announce Type: replace-cross Abstract: Flow-based generative models can be viewed through a physics lens: sampling transports a particle from noise to data by integrating a learned
arXiv:2509.10114v2 Announce Type: replace Abstract: Face image quality assessment (FIQA) plays a critical role in face recognition and verification systems, especially in uncontrolled, real-world envi
arXiv:2605.30510v1 Announce Type: cross Abstract: Brain cancer's severity necessitates precise brain tumor segmentation, which is crucial for effective brain tumor diagnosis. Manual identification, bu
arXiv:2605.30452v1 Announce Type: cross Abstract: Many machine learning problems involve multiple inherent trade-offs that are best addressed by gradient-based multi-objective optimization (MOO) algor