Stay updated with the latest research and technology news
arXiv:2509.21730v2 Announce Type: replace Abstract: As large language models (LLMs) become increasingly integrated into daily life, there is growing demand for AI assistants that are...
arXiv:2509.21896v2 Announce Type: replace Abstract: Recent neuro-symbolic geometry theorem provers have made significant progress on Euclidean problems by coupling neural guidance with symbolic verification. However,...
arXiv:2509.21990v2 Announce Type: replace Abstract: While embeddings from multimodal large language models (LLMs) excel as general-purpose representations, their application to dynamic modalities like audio and...
arXiv:2509.22166v2 Announce Type: replace Abstract: The demand for efficient large language model (LLM) inference has intensified the focus on sparsification techniques. While semi-structured (N:M) pruning...
arXiv:2509.22295v5 Announce Type: replace Abstract: Cross-domain generalization is very important in Time Series Forecasting because similar historical information may lead to distinct future trends due...
arXiv:2509.22387v2 Announce Type: replace Abstract: The Counterfactual Regret Minimization (CFR) algorithm and its variants have enabled the development of pokerbots capable of beating the best...
arXiv:2509.23040v4 Announce Type: replace Abstract: Large language models face challenges in long-context question answering, where key evidence of a query may be dispersed across millions...
arXiv:2509.23106v3 Announce Type: replace Abstract: The Muon optimizer, based on matrix orthogonalization, has recently shown faster convergence and better computational efficiency over AdamW in LLM...
arXiv:2509.23184v3 Announce Type: replace Abstract: The remarkable success of Chain-of-Thought (CoT), which enhances performance by scaling generation steps at test-time, inspires us to ask: can...
arXiv:2509.23575v2 Announce Type: replace Abstract: Hierarchical coarse-to-fine policy, where a coarse branch predicts a region of interest to guide a fine-grained action predictor, has demonstrated...
arXiv:2509.24228v2 Announce Type: replace Abstract: Positive-unlabeled (PU) learning is a weakly supervised binary classification problem, in which the goal is to learn a binary classifier...
arXiv:2509.24243v3 Announce Type: replace Abstract: Generative planners based on flow matching (FM) produce high-quality paths in a single or a few ODE steps, but their...
arXiv:2509.24526v2 Announce Type: replace Abstract: Flow map models such as Consistency Models (CM) and Mean Flow (MF) enable few-step generation by learning the long jump...
arXiv:2509.24837v2 Announce Type: replace Abstract: Large Vision-Language Models (VLMs) enable strong multimodal reasoning but incur heavy inference costs from redundant visual tokens. Token pruning alleviates...
arXiv:2509.25162v2 Announce Type: replace Abstract: In this work, we propose aligning pretrained visual encoders to serve as tokenizers for latent diffusion models in image generation....
arXiv:2509.25210v2 Announce Type: replace Abstract: To gain finer regional forecasts, many works have explored the regional integration from the global atmosphere, e.g., by solving boundary...
arXiv:2509.25411v2 Announce Type: replace Abstract: We propose ImitSAT, a branching policy for conflict-driven clause learning (CDCL) solvers based on imitation learning for the Boolean satisfiability...
arXiv:2509.25424v2 Announce Type: replace Abstract: Reinforcement learning fine-tuning (RLFT) is a dominant paradigm for improving pretrained policies for downstream tasks. These pretrained policies, trained on...
arXiv:2509.25723v3 Announce Type: replace Abstract: Visual Place Recognition (VPR) requires robust retrieval of geotagged images despite large appearance, viewpoint, and environmental variation. Prior methods focus...
arXiv:2509.26209v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a crucial paradigm for incentivizing reasoning capabilities in Large Language Models...
arXiv:2509.26287v2 Announce Type: replace Abstract: We introduce Flower, a solver for linear inverse problems. It leverages a pre-trained flow model to produce reconstructions that are...
arXiv:2509.26308v3 Announce Type: replace Abstract: Out-of-distribution states in robot manipulation often lead to unpredictable robot behavior or task failure, limiting success rates and increasing risk...
arXiv:2509.26518v2 Announce Type: replace Abstract: Mean-shift-based approaches have recently emerged as a representative class of methods for robot swarm shape assembly. They rely on image-based...
arXiv:2510.00502v2 Announce Type: replace Abstract: Diffusion alignment aims to optimize diffusion models for the downstream objective. While existing methods based on reinforcement learning or direct...