CUEBES

DEBATE: A Large-Scale Benchmark for Evaluating Opinion Dynamics in Role-Playing LLM Agents

arXiv:2510.25110v4 Announce Type: replace Abstract: Accurately modeling opinion change through social interactions is crucial for understanding and mitigating polarization, misinformation, and societal conflict. Recent work...

Technology Psychology

arXiv CS Feb 6

TempoPFN: Synthetic Pre-training of Linear RNNs for Zero-shot Time Series Forecasting

arXiv:2510.25502v4 Announce Type: replace Abstract: Foundation models for zero-shot time series forecasting face challenges in efficient long-horizon prediction and reproducibility, with existing synthetic-only approaches underperforming...

Software Technology

arXiv CS Feb 6

Learning to Plan & Schedule with Reinforcement-Learned Bimanual Robot Skills

arXiv:2510.25634v2 Announce Type: replace Abstract: Long-horizon contact-rich bimanual manipulation presents a significant challenge, requiring complex coordination involving a mixture of parallel execution and sequential collaboration...

Robotics Psychology

arXiv CS Feb 6

All You Need for Object Detection: From Pixels, Points, and Prompts to Next-Gen Fusion and Multimodal LLMs/VLMs in Autonomous Vehicles

arXiv:2510.26641v3 Announce Type: replace Abstract: Autonomous Vehicles (AVs) are transforming the future of transportation through advances in intelligent perception, decision-making, and control systems. However, their...

Artificial Intelligence Energy

arXiv CS Feb 6

Cut-free Deductive System for Continuous Intuitionistic Logic

arXiv:2510.26849v4 Announce Type: replace Abstract: We introduce and develop propositional continuous intuitionistic logic and propositional continuous affine logic via complete algebraic semantics. Our approach centres...

Software Mathematics

arXiv CS Feb 6

Remembering Unequally: Global and Disciplinary Bias in LLM Reconstruction of Scholarly Coauthor Lists

arXiv:2511.00476v2 Announce Type: replace Abstract: Ongoing breakthroughs in large language models (LLMs) are reshaping scholarly search and discovery interfaces. While these systems offer new possibilities...

World News Medicine & Health

arXiv CS Feb 6

Test-Time Iterative Error Correction for Efficient Diffusion Models

arXiv:2511.06250v2 Announce Type: replace Abstract: With the growing demand for high-quality image generation on resource-constrained devices, efficient diffusion models have received increasing attention. However, such...

Technology Environment

arXiv CS Feb 6

Data Heterogeneity and Forgotten Labels in Split Federated Learning

arXiv:2511.09736v2 Announce Type: replace Abstract: In Split Federated Learning (SFL), the clients collaboratively train a model with the help of a server by splitting the...

Neuroscience World News

arXiv CS Feb 6

Text2SQL-Flow: A Robust SQL-Aware Data Augmentation Framework for Text-to-SQL

arXiv:2511.10192v3 Announce Type: replace Abstract: The data-centric paradigm has become pivotal in AI, especially for Text-to-SQL, where performance is limited by scarce, simplistic, and low-diversity...

Technology Engineering

arXiv CS Feb 6

VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Models

arXiv:2511.11007v2 Announce Type: replace Abstract: Despite the remarkable success of Vision-Language Models (VLMs), their performance on a range of complex visual tasks is often hindered...

Neuroscience Software

arXiv CS Feb 6

Novel Stability Criteria for Discrete and Hybrid Systems via Ramanujan Inner Products

arXiv:2511.13690v2 Announce Type: replace Abstract: This paper introduces a Ramanujan inner product and its corresponding norm, establishing a novel framework for the stability analysis of...

Psychology Software

arXiv CS Feb 6

Your Latent Reasoning is Secretly Policy Improvement Operator

arXiv:2511.16886v4 Announce Type: replace Abstract: Recently, small models with latent recursion have obtained promising results on complex reasoning tasks. These results are typically explained by...

Policy Psychology

arXiv CS Feb 6

REArtGS++: Generalizable Articulation Reconstruction with Temporal Geometry Constraint via Planar Gaussian Splatting

arXiv:2511.17059v3 Announce Type: replace Abstract: Articulated objects are pervasive in daily environments, such as drawers and refrigerators. Towards their part-level surface reconstruction and joint parameter...

Environment Software

arXiv CS Feb 6

UAM: A Unified Attention-Mamba Backbone of Multimodal Framework for Tumor Cell Classification

arXiv:2511.17355v2 Announce Type: replace Abstract: Inspired by the recent success of the Mamba architecture in vision and language domains, we introduce a Unified Attention-Mamba (UAM)...

Software Psychology

arXiv CS Feb 6

Opt4GPTQ: Co-Optimizing Memory and Computation for 4-bit GPTQ Quantized LLM Inference on Heterogeneous Platforms

arXiv:2511.19438v2 Announce Type: replace Abstract: The increasing adoption of large language models (LLMs) on heterogeneous computing platforms poses significant challenges to achieving high inference efficiency....

Hardware Artificial Intelligence

arXiv CS Feb 6

Approximating Analytically-Intractable Likelihood Densities with Deterministic Arithmetic for Optimal Particle Filtering

arXiv:2512.01023v2 Announce Type: replace Abstract: Particle filtering algorithms have enabled practical solutions to problems in autonomous robotics (self-driving cars, UAVs, warehouse robots), target tracking, and...

Robotics Software

arXiv CS Feb 6

CARL: Focusing Agentic Reinforcement Learning on Critical Actions

arXiv:2512.04949v2 Announce Type: replace Abstract: Agents capable of accomplishing complex tasks through multiple interactions with the environment have emerged as a popular research direction. However,...

Policy Environment

arXiv CS Feb 6

Sparse Attention Post-Training for Mechanistic Interpretability

arXiv:2512.05865v2 Announce Type: replace Abstract: We introduce a simple post-training method that makes transformer attention sparse without sacrificing performance. Applying a flexible sparsity regularisation under...

Software Engineering

arXiv CS Feb 6

Vector Quantization using Gaussian Variational Autoencoder

arXiv:2512.06609v2 Announce Type: replace Abstract: Vector-quantized variational autoencoders (VQ-VAEs) are discrete autoencoders that compress images into discrete tokens. However, they are difficult to train due...

Materials Science Technology

arXiv CS Feb 6

WebSTAR: Scalable Data Synthesis for Computer Use Agents with Step-Level Filtering

arXiv:2512.10962v3 Announce Type: replace Abstract: Computer use agents (CUAs) can operate real-world digital interfaces but remain difficult to train due to the high cost of...

Technology Chemistry

arXiv CS Feb 6

Bandit-Based Rate Adaptation for a Single-Server Queue

arXiv:2512.12016v2 Announce Type: replace Abstract: This paper considers the problem of obtaining bounded time-average expected queue sizes in a single-queue system with a partial-feedback structure....

Policy Environment

arXiv CS Feb 6

MRD: Using Physically Based Differentiable Rendering to Probe Vision Models for 3D Scene Understanding

arXiv:2512.12307v2 Announce Type: replace Abstract: While deep learning methods have achieved impressive success in many vision benchmarks, it remains difficult to understand and explain the...

Materials Science Software

arXiv CS Feb 6

Fine-tuned LLM-based Code Migration Framework

arXiv:2512.13515v3 Announce Type: replace Abstract: The study presents the outcomes of research and experimental validation in the domain of automated codebase migration, with a focus...

Technology Software

arXiv CS Feb 6

MindDrive: A Vision-Language-Action Model for Autonomous Driving via Online Reinforcement Learning

arXiv:2512.13636v3 Announce Type: replace Abstract: Current Vision-Language-Action (VLA) paradigms in autonomous driving primarily rely on Imitation Learning (IL), which introduces inherent challenges such as distribution...

Robotics Psychology