Hybrid Training for Vision-Language-Action Models
arXiv:2510.00600v2 Announce Type: replace-cross Abstract: Using Large Language Models to produce intermediate thoughts, a.k.a. Chain-of-thought (CoT), before providing an answer has been a successful
Knowledge catalogue
arXiv:2510.00600v2 Announce Type: replace-cross Abstract: Using Large Language Models to produce intermediate thoughts, a.k.a. Chain-of-thought (CoT), before providing an answer has been a successful
arXiv:2605.19301v1 Announce Type: new Abstract: Vision-Language Models require efficient adaptation to continually emerging downstream tasks. While Parameter-Efficient Fine-Tuning mitigates catastroph
arXiv:2603.29183v2 Announce Type: replace-cross Abstract: Open-set anomaly detection (OSAD) is an emerging paradigm designed to utilize limited labeled data from anomaly classes seen in training to id
arXiv:2605.19592v1 Announce Type: cross Abstract: Reinforcement learning often produces high-frequency oscillatory control signals that undermine the safety and stability required for physical deploym
arXiv:2605.19644v1 Announce Type: cross Abstract: Knowledge Graphs (KGs) are a powerful representation of linked data, offering flexibility, semantic richness, and support for knowledge enrichment and
arXiv:2605.20088v1 Announce Type: cross Abstract: Discovering shapelets -- i.e., discriminative temporal patterns within time series -- has been widely studied to address the inherent complexity of ti
arXiv:2605.19042v1 Announce Type: new Abstract: Machine unlearning aims to remove the contribution of designated training data from a trained model while preserving performance on the remaining data.
arXiv:2605.19982v1 Announce Type: new Abstract: Low-Light Image Enhancement (LLIE) has long been a challenging problem in low-level vision, as insufficient illumination often leads to low contrast, de
As models and harnesses improve, agents are taking on increasingly complex tasks that can run for hours or even days. But as we push agents to do more, this has surfaced a new operational problem: lon
arXiv:2605.20108v1 Announce Type: cross Abstract: While conventional (k=1) discrete-time barrier certificate conditions impose strict safety constraints by requiring the function to be non-increasing
arXiv:2605.19435v1 Announce Type: cross Abstract: Visual Place Recognition (VPR) is critical for autonomous navigation, yet state-of-the-art methods lack well-calibrated uncertainty estimation. Standa
arXiv:2605.18895v1 Announce Type: cross Abstract: Safety validation of autonomous driving systems requires high-risk scenario coverage, clear collision semantics, executable trajectories, and attribut
arXiv:2605.19703v1 Announce Type: new Abstract: Autonomous UAV flight in confined, wall-dense environments requires low-latency and reliable motion planning under strict safety constraints. Traditiona
arXiv:2605.19416v1 Announce Type: new Abstract: Group Relative Policy Optimization(GRPO) has become a cornerstone of modern reinforcement learning alignment, prized for its efficacy in foregoing an ex
arXiv:2507.01123v2 Announce Type: replace Abstract: Landslides pose severe threats to infrastructure, economies, and human lives, necessitating accurate detection and predictive mapping across diverse
arXiv:2605.19284v1 Announce Type: new Abstract: In the training data used by large language models (LLMs), the same latent concept is often presented in multiple distinct ways: the same facts appear i
arXiv:2605.19805v1 Announce Type: cross Abstract: Irregular multivariate time series impose a trade-off for long-horizon forecasting: discrete methods can distort temporal structure via re-gridding, w
arXiv:2506.01529v2 Announce Type: replace Abstract: Learning meaningful abstract models of Markov Decision Processes (MDPs) is crucial for improving generalization from limited data. In this work, we
arXiv:2510.03485v2 Announce Type: replace Abstract: Autonomous web agents are increasingly deployed for long-horizon tasks, yet their ability to adhere to real-world policies remains critically undere
arXiv:2605.19074v1 Announce Type: cross Abstract: The rapid global expansion of solar photovoltaic (PV) capacity-reaching a record 597 GW in 2024-highlights the urgent need for robust forecasting mode
arXiv:2605.19959v1 Announce Type: new Abstract: Infinite-dimensional orthonormal basis expansions play a central role in representing and computing with function spaces due to their favorable linear a
arXiv:2605.19140v1 Announce Type: new Abstract: We study workflow learning in a setting where specialized agents hand off control through a shared artifact, each agent observes only a local function o
arXiv:2605.19578v1 Announce Type: cross Abstract: RGB camera-based surveillance systems enable human action recognition for public safety and healthcare, yet raise serious privacy concerns. Existing m
arXiv:2605.19060v1 Announce Type: cross Abstract: High-resolution 3D medical image generation remains challenging because fully volumetric models are computationally expensive, while efficient 2D slic
arXiv:2605.18907v1 Announce Type: cross Abstract: Deep neural networks (DNN), despite their remarkable performance, are highly vulnerable to backdoor attacks. Existing defenses mainly rely on activati
arXiv:2601.03645v2 Announce Type: replace Abstract: Emotional coordination is a core property of human interaction that shapes how relational meaning is constructed in real time. While text-based affe
arXiv:2603.16284v2 Announce Type: replace Abstract: Despite the significant advancements in Large Vision-Language Models (LVLMs), their tendency to generate hallucinations undermines reliability and r
arXiv:2605.18846v1 Announce Type: cross Abstract: Classical communication systems fail not only through random noise but also when transmitter and receiver use incompatible operational codebooks. Vari
LTX 2.3 IC introduces specialized LoRA (Low-Rank Adaptation) modules for video generation, including LipDub functionality for synchronized lip movements and Video Utilities for enhanced video processi
arXiv:2605.19080v1 Announce Type: cross Abstract: In Online Continual Learning (OCL), a neural network sequentially learns from a non-stationary data stream in a single-pass with access only to a limi
arXiv:2605.19723v1 Announce Type: cross Abstract: Mathematical reasoning is essential for problem-solving in education, science, and industry, serving as a crucial benchmark for evaluating artificial
arXiv:2605.19386v1 Announce Type: new Abstract: Reconstructing simulation-ready deformable objects is important for vision, graphics, and robotics. Existing physics-driven methods can recover physical
arXiv:2605.19594v1 Announce Type: new Abstract: Navigating to instance-level targets in complex environments is a challenging problem. Many existing zero-shot methods achieve strong performance by mod
arXiv:2506.18852v2 Announce Type: replace-cross Abstract: Mechanistic interpretability (MI) aims to explain how neural networks work by uncovering their underlying mechanisms. As the field grows in in
arXiv:2605.19833v1 Announce Type: cross Abstract: Despite rapid advances in automatic speech recognition (ASR) and large audio-language models, robust recognition in real-world environments remains li
arXiv:2605.19307v1 Announce Type: new Abstract: Visual Question Answering (VQA), as the representative multimodal task, serves as a key benchmark for evaluating the reasoning capabilities of Multimoda
arXiv:2605.19304v1 Announce Type: new Abstract: While 3D Gaussian Splatting (3DGS) has revolutionized 3D reconstruction, it suffers from significant overhead due to massive redundant primitives. Exist
arXiv:2412.13111v2 Announce Type: replace Abstract: Text-driven human motion synthesis has showcased its potential for revolutionizing motion design in the movie and game industry. Existing methods of
arXiv:2605.19752v1 Announce Type: new Abstract: Accurately identifying metabolites i.e. small molecules from mass spectrometry data remains a core challenge in metabolomics, with broad applications in
arXiv:2605.19430v1 Announce Type: new Abstract: Flapping-Wing Micro Aerial Vehicles (FWMAVs) provide exceptional maneuverability and aerodynamic efficiency but pose significant challenges for onboard
arXiv:2605.20098v1 Announce Type: new Abstract: Claim verification is an important problem in high-stakes settings, including health and finance. When information underpinning claims is incomplete or
arXiv:2510.18924v3 Announce Type: replace-cross Abstract: Reinforcement learning from human feedback (RLHF) or verifiable rewards (RLVR), the standard paradigm for aligning LLMs or building recent SOT
arXiv:2605.20164v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has made post-training highly effective when correctness can be checked automatically. However, many impo
arXiv:2605.18758v1 Announce Type: cross Abstract: Current benchmarks for graphical user interface (GUI) agents predominantly rely on static screenshots. However, real-world smartphone interaction rout
arXiv:2511.22940v3 Announce Type: replace Abstract: Recent advances in diffusion models have greatly improved pose-driven character animation. However, existing methods are limited to spatially aligne
arXiv:2605.19633v1 Announce Type: cross Abstract: Can a single LLM-based optimization system match specialized tools across fundamentally different domains? We show that when optimization problems are
arXiv:2605.19634v1 Announce Type: cross Abstract: Vision-and-language navigation (VLN) requires an embodied agent to ground natural-language instructions into executable navigation actions in unseen e
arXiv:2605.19932v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly operate over long and recurring external contexts, like document corpora and code repositories. Across in
arXiv:2409.03192v2 Announce Type: replace Abstract: Fine-grained image classification has witnessed significant advancements with the advent of deep learning and computer vision technologies. However,
arXiv:2605.19107v1 Announce Type: new Abstract: Green hydrogen plays an essential role in decarbonization, with capacity projected to scale to 560 GW by 2030 (vs. 1.39 GW in 2023) in net-zero settings
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:2508.06526v3 Announce Type: replace-cross Abstract: As large-scale language models continue to scale up in both size and context length, the memory and communication cost of key-value (KV) cache
arXiv:2605.19145v1 Announce Type: new Abstract: In the literature, many continual learning (CL) algorithms have been proposed to address the issue of catastrophic forgetting in ML models (i.e., learni
arXiv:2605.19610v1 Announce Type: cross Abstract: We investigate the asymptotic properties of the Levy Adaptive B-spline (LABS) regression model, a Bayesian nonparametric method that incorporates B-sp
arXiv:2605.19382v1 Announce Type: new Abstract: Programmatic video generation through code offers geometric precision and temporal coherence beyond pixel-level diffusion models, yet rigorously evaluat
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:2605.19015v1 Announce Type: cross Abstract: Safe motion planning in uncertain, time-varying environments is challenging because the safe region can change unpredictably across planning steps, of
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:2605.19549v1 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:2605.19052v1 Announce Type: cross Abstract: Lagrangian Relaxation (LR) is a powerful technique for solving large-scale Mixed Integer Linear Programming (MILP), particularly those with decomposab