Menu
arxiv_ai

Learning World Models for Interactive Video Generation

Abstract: Abstract: Foundational world models must be both interactive and preserve spatiotemporal coherence for effective future planning with action choices. However, present models for long video generation have limited inherent world modeling capabilities ...
5 days ago
50%
arxiv_ai

Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers

Abstract: Abstract: Academic poster generation is a crucial yet challenging task in scientific communication, requiring the compression of long-context interleaved documents into a single, visually coherent page. To address this challenge, we introduce the fir...
5 days ago
50%
arxiv_ai

Towards Predicting Any Human Trajectory In Context

Abstract: Abstract: Predicting accurate future trajectories of pedestrians is essential for autonomous systems but remains a challenging task due to the need for adaptability in different environments and domains. A common approach involves collecting scenario...
5 days ago
50%
arxiv_ai

Efficient Regression-Based Training of Normalizing Flows for Boltzmann Generators

Abstract: Abstract: Simulation-free training frameworks have been at the forefront of the generative modelling revolution in continuous spaces, leading to large-scale diffusion and flow matching models. However, such modern generative models suffer from expens...
5 days ago
50%
arxiv_ai

Incentivizing LLMs to Self-Verify Their Answers

Abstract: Abstract: Large Language Models (LLMs) have demonstrated remarkable progress in complex reasoning tasks through both post-training and test-time scaling laws. While prevalent test-time scaling approaches are often realized by using external reward mo...
5 days ago
50%
arxiv_ai

UniSite: The First Cross-Structure Dataset and Learning Framework for End-to-End Ligand Binding Site Detection

Abstract: Abstract: The detection of ligand binding sites for proteins is a fundamental step in Structure-Based Drug Design. Despite notable advances in recent years, existing methods, datasets, and evaluation metrics are confronted with several key challenges...
5 days ago
50%
arxiv_ai

GenIR: Generative Visual Feedback for Mental Image Retrieval

Abstract: Abstract: Vision-language models (VLMs) have shown strong performance on text-to-image retrieval benchmarks. However, bridging this success to real-world applications remains a challenge. In practice, human search behavior is rarely a one-shot action...
5 days ago
50%
arxiv_ai

Human-assisted Robotic Policy Refinement via Action Preference Optimization

Abstract: Abstract: Establishing a reliable and iteratively refined robotic system is essential for deploying real-world applications. While Vision-Language-Action (VLA) models are widely recognized as the foundation model for such robotic deployment, their re...
5 days ago
50%
arxiv_ai

SAFE: Multitask Failure Detection for Vision-Language-Action Models

Abstract: Abstract: While vision-language-action models (VLAs) have shown promising robotic behaviors across a diverse set of manipulation tasks, they achieve limited success rates when deployed on novel tasks out of the box. To allow these policies to safely ...
5 days ago
50%
arxiv_ai

SPARKE: Scalable Prompt-Aware Diversity and Novelty Guidance in Diffusion Models via RKE Score

Abstract: Abstract: Diffusion models have demonstrated remarkable success in high-fidelity image synthesis and prompt-guided generative modeling. However, ensuring adequate diversity in generated samples of prompt-guided diffusion models remains a challenge, p...
5 days ago
50%
arxiv_ml

Exact Sequence Interpolation with Transformers

Abstract: Abstract: We prove that transformers can exactly interpolate datasets of finite input sequences in $\mathbb{R}^d$, $d\geq 2$, with corresponding output sequences of smaller or equal length. Specifically, given $N$ sequences of arbitrary but finite le...
6 days ago
50%
arxiv_ml

TuneNSearch: a hybrid transfer learning and local search approach for solving vehicle routing problems

Abstract: Abstract: This paper introduces TuneNSearch, a hybrid transfer learning and local search approach for addressing diverse variants of the vehicle routing problem (VRP). Our method uses reinforcement learning to generate high-quality solutions, which a...
6 days ago
50%
arxiv_ml

ASGO: Adaptive Structured Gradient Optimization

Abstract: Abstract: Training deep neural networks is a structured optimization problem, because the parameters are naturally represented by matrices and tensors rather than by vectors. Under this structural representation, it has been widely observed that grad...
6 days ago
50%
arxiv_ml

Enlightenment Period Improving DNN Performance

Abstract: Abstract: The start of deep neural network training is characterized by a brief yet critical phase that lasts from the beginning of the training until the accuracy reaches approximately 50\%. During this phase, disordered representations rapidly tran...
6 days ago
50%
arxiv_ml

MDPs with a State Sensing Cost

Abstract: Abstract: In many practical sequential decision-making problems, tracking the state of the environment incurs a sensing/communication/computation cost. In these settings, the agent's interaction with its environment includes the additional component ...
6 days ago
50%
arxiv_ml

Spectral Perturbation Bounds for Low-Rank Approximation with Applications to Privacy

Abstract: Abstract: A central challenge in machine learning is to understand how noise or measurement errors affect low-rank approximations, particularly in the spectral norm. This question is especially important in differentially private low-rank approximati...
6 days ago
0%
arxiv_ml

Q-learning with Posterior Sampling

Abstract: Abstract: Bayesian posterior sampling techniques have demonstrated superior empirical performance in many exploration-exploitation settings. However, their theoretical analysis remains a challenge, especially in complex settings like reinforcement le...
6 days ago
50%
arxiv_ml

Stochastic Momentum Methods for Non-smooth Non-Convex Finite-Sum Coupled Compositional Optimization

Abstract: Abstract: Finite-sum Coupled Compositional Optimization (FCCO), characterized by its coupled compositional objective structure, emerges as an important optimization paradigm for addressing a wide range of machine learning problems. In this paper, we ...
6 days ago
50%
arxiv_ml

Learning single-index models via harmonic decomposition

Abstract: Abstract: We study the problem of learning single-index models, where the label $y \in \mathbb{R}$ depends on the input $\boldsymbol{x} \in \mathbb{R}^d$ only through an unknown one-dimensional projection $\langle \boldsymbol{w}_*,\boldsymbol{x}\rang...
6 days ago
50%
arxiv_ml

Path-specific effects for pulse-oximetry guided decisions in critical care

Abstract: Abstract: Identifying and measuring biases associated with sensitive attributes is a crucial consideration in healthcare to prevent treatment disparities. One prominent issue is inaccurate pulse oximeter readings, which tend to overestimate oxygen sa...
6 days ago
50%
arxiv_ml

Why Knowledge Distillation Works in Generative Models: A Minimal Working Explanation

Abstract: Abstract: Knowledge distillation (KD) is a core component in the training and deployment of modern generative models, particularly large language models (LLMs). While its empirical benefits are well documented -- enabling smaller student models to em...
6 days ago
50%
arxiv_ml

Neural Guided Sampling for Quantum Circuit Optimization

Abstract: Abstract: Translating a general quantum circuit on a specific hardware topology with a reduced set of available gates, also known as transpilation, comes with a substantial increase in the length of the equivalent circuit. Due to decoherence, the qua...
2 weeks ago
50%
arxiv_ml

Geopolitics, Geoeconomics and Risk:A Machine Learning Approach

Abstract: Abstract: We introduce a novel high-frequency daily panel dataset of both markets and news-based indicators -- including Geopolitical Risk, Economic Policy Uncertainty, Trade Policy Uncertainty, and Political Sentiment -- for 42 countries across both...
2 weeks ago
50%
arxiv_ml

Robot Learning: A Tutorial

Abstract: Abstract: Robot learning is at an inflection point, driven by rapid advancements in machine learning and the growing availability of large-scale robotics data. This shift from classical, model-based methods to data-driven, learning-based paradigms is...
2 weeks ago
50%
arxiv_ml

Improving Generative Behavior Cloning via Self-Guidance and Adaptive Chunking

Abstract: Abstract: Generative Behavior Cloning (GBC) is a simple yet effective framework for robot learning, particularly in multi-task settings. Recent GBC methods often employ diffusion policies with open-loop (OL) control, where actions are generated via a...
2 weeks ago
50%
arxiv_ml

Improved Central Limit Theorem and Bootstrap Approximations for Linear Stochastic Approximation

Abstract: Abstract: In this paper, we refine the Berry-Esseen bounds for the multivariate normal approximation of Polyak-Ruppert averaged iterates arising from the linear stochastic approximation (LSA) algorithm with decreasing step size. We consider the norma...
2 weeks ago
50%
arxiv_ml

Constrained Sensing and Reliable State Estimation with Shallow Recurrent Decoders on a TRIGA Mark II Reactor

Abstract: Abstract: Shallow Recurrent Decoder networks are a novel data-driven methodology able to provide accurate state estimation in engineering systems, such as nuclear reactors. This deep learning architecture is a robust technique designed to map the tem...
2 weeks ago
50%
arxiv_ml

Locket: Robust Feature-Locking Technique for Language Models

Abstract: Abstract: Chatbot providers (e.g., OpenAI) rely on tiered subscription schemes to generate revenue, offering basic models for free users, and advanced models for paying subscribers. However, a finer-grained pay-to-unlock scheme for premium features (...
2 weeks ago
50%
arxiv_ml

FedLoDrop: Federated LoRA with Dropout for Generalized LLM Fine-tuning

Abstract: Abstract: Fine-tuning (FT) large language models (LLMs) is crucial for adapting general-purpose models to specific tasks, enhancing accuracy and relevance with minimal resources. To further enhance generalization ability while reducing training costs...
2 weeks ago
50%
arxiv_ml

Compressibility Measures Complexity: Minimum Description Length Meets Singular Learning Theory

Abstract: Abstract: We study neural network compressibility by using singular learning theory to extend the minimum description length (MDL) principle to singular models like neural networks. Through extensive experiments on the Pythia suite with quantization,...
2 weeks ago
50%

Loading more papers...

📚 You've reached the end of the papers list