CUEBES

Adaptive Helpfulness-Harmlessness Alignment with Preference Vectors

arXiv:2504.20106v3 Announce Type: replace Abstract: Ensuring that large language models (LLMs) are both helpful and harmless is a critical challenge, as overly strict constraints can...

Psychology Software

arXiv CS Feb 5

Sparse-to-Sparse Training of Diffusion Models

arXiv:2504.21380v2 Announce Type: replace Abstract: Diffusion models (DMs) are a powerful type of generative models that have achieved state-of-the-art results in various image synthesis tasks...

Energy Chemistry

arXiv CS Feb 5

Dynamic and Distributed Routing in IoT Networks based on Multi-Objective Q-Learning

arXiv:2505.00918v4 Announce Type: replace Abstract: IoT networks often face conflicting routing goals such as maximizing packet delivery, minimizing delay, and conserving limited battery energy. These...

Energy Policy

arXiv CS Feb 5

Comparing statistical and deep learning techniques for parameter estimation of continuous-time stochastic differentiable equations

arXiv:2505.03980v2 Announce Type: replace Abstract: Stochastic differential equations such as the Ornstein-Uhlenbeck process have long been used to model realworld probablistic events such as stock...

Technology Artificial Intelligence

arXiv CS Feb 5

Improved Bag-of-Words Image Retrieval with Geometric Constraints for Ground Texture Localization

arXiv:2505.11620v2 Announce Type: replace Abstract: Ground texture localization using a downward-facing camera offers a low-cost, high-precision localization solution that is robust to dynamic environments and...

Environment Psychology

arXiv CS Feb 5

RL in Name Only? Analyzing the Structural Assumptions in RL post-training for LLMs

arXiv:2505.13697v4 Announce Type: replace Abstract: Reinforcement learning based post-training of large language models (LLMs) has recently gained attention, particularly following the release of DeepSeek R1,...

Policy Engineering

arXiv CS Feb 5

LoVR: A Benchmark for Long Video Retrieval in Multimodal Contexts

arXiv:2505.13928v4 Announce Type: replace Abstract: Long videos contain a vast amount of information, making video-text retrieval an essential and challenging task in multimodal learning. However,...

Software Energy

arXiv CS Feb 5

Entailed Opinion Matters: Improving the Fact-Checking Performance of Language Models by Relying on their Entailment Ability

arXiv:2505.15050v4 Announce Type: replace Abstract: Automated fact-checking has been a challenging task for the research community. Past works tried various strategies, such as end-to-end training,...

Engineering Software

arXiv CS Feb 5

PaTH Attention: Position Encoding via Accumulating Householder Transformations

arXiv:2505.16381v2 Announce Type: replace Abstract: The attention mechanism is a core primitive in modern large language models (LLMs) and AI more broadly. Since attention by...

Artificial Intelligence Genetics

arXiv CS Feb 5

A Chase-based Approach to Consistent Answers of Analytic Queries in Star Schemas

arXiv:2505.16802v2 Announce Type: replace Abstract: We present an approach to computing consistent answers to queries possibly involving an aggregation operator in databases operating under a...

Software Politics

arXiv CS Feb 5

VEAttack: Downstream-agnostic Vision Encoder Attack against Large Vision Language Models

arXiv:2505.17440v2 Announce Type: replace Abstract: Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in multimodal understanding and generation, yet their vulnerability to adversarial attacks raises...

Software Policy

arXiv CS Feb 5

Language models can learn implicit multi-hop reasoning, but only if they have lots of training data

arXiv:2505.17923v2 Announce Type: replace Abstract: Implicit reasoning is the ability of a language model to solve multi-hop reasoning tasks in a single forward pass, without...

Policy Artificial Intelligence

arXiv CS Feb 5

Early-Exit Graph Neural Networks

arXiv:2505.18088v2 Announce Type: replace Abstract: Early-exit mechanisms allow deep neural networks to stop inference once prediction confidence is high, reducing latency and energy on easy...

Neuroscience Software

arXiv CS Feb 5

Toward Multiphysics-Informed Machine Learning for Sustainable Data Center Operations: Intelligence Evolution with Deployable Solutions for Computing Infrastructure

arXiv:2505.19414v2 Announce Type: replace Abstract: The revolution in artificial intelligence (AI) has brought sustainable challenges in data center management due to the high carbon emissions...

Climate & Environment Software

arXiv CS Feb 5

HAODiff: Human-Aware One-Step Diffusion via Dual-Prompt Guidance

arXiv:2505.19742v2 Announce Type: replace Abstract: Human-centered images often suffer from severe generic degradation during transmission and are prone to human motion blur (HMB), making restoration...

Software Energy

arXiv CS Feb 5

Evaluating and Steering Modality Preferences in Multimodal Large Language Model

arXiv:2505.20977v3 Announce Type: replace Abstract: Multi-modal large language models (MLLMs) have achieved remarkable success on complex multi-modal tasks. However, it remains insufficiently explored whether they...

Engineering Policy

arXiv CS Feb 5

Are Graph Attention Networks Able to Model Structural Information?

arXiv:2505.21288v2 Announce Type: replace Abstract: Graph Attention Networks (GATs) have emerged as powerful models for learning expressive representations from such data by adaptively weighting neighboring...

Software Engineering

arXiv CS Feb 5

CodeSense: a Real-World Benchmark and Dataset for Code Semantic Reasoning

arXiv:2506.00750v3 Announce Type: replace Abstract: Understanding and reasoning about code semantics is essential for enhancing code LLMs' abilities to solve real-world software engineering (SE) tasks....

Technology Engineering

arXiv CS Feb 5

What's Missing in Vision-Language Models? Probing Their Struggles with Causal Order Reasoning

arXiv:2506.00869v2 Announce Type: replace Abstract: Despite the impressive performance of vision-language models (VLMs) on downstream tasks, their ability to understand and reason about causal relationships...

Psychology Policy

arXiv CS Feb 5

GRAM: Spatial general-purpose audio representation models for real-world applications

arXiv:2506.00934v5 Announce Type: replace Abstract: Audio foundation models learn general-purpose audio representations that facilitate a wide range of downstream tasks. While the performance of these...

Software Environment

arXiv CS Feb 5

REASONING COMPILER: LLM-Guided Optimizations for Efficient Model Serving

arXiv:2506.01374v5 Announce Type: replace Abstract: While model serving has unlocked unprecedented capabilities, the high cost of serving large-scale models continues to be a significant barrier...

Hardware Technology

arXiv CS Feb 5

Generalized Gradient Norm Clipping & Non-Euclidean $(L_0,L_1)$-Smoothness

arXiv:2506.01913v3 Announce Type: replace Abstract: This work introduces a hybrid non-Euclidean optimization method which generalizes gradient norm clipping by combining steepest descent and conditional gradient...

Software Artificial Intelligence

arXiv CS Feb 5

RETENTION: Resource-Efficient Tree-Based Ensemble Model Acceleration with Content-Addressable Memory

arXiv:2506.05994v2 Announce Type: replace Abstract: Although deep learning has demonstrated remarkable capability in learning from unstructured data, modern tree-based ensemble models remain superior in extracting...

Artificial Intelligence Psychology

arXiv CS Feb 5

Graph Persistence goes Spectral

arXiv:2506.06571v3 Announce Type: replace Abstract: Including intricate topological information (e.g., cycles) provably enhances the expressivity of message-passing graph neural networks (GNNs) beyond the Weisfeiler-Leman (WL)...

World News Neuroscience