SocietyBench: Forecasting Counterfactual Social-World Evolution
arXiv:2608.04009v2 Announce Type: replace Abstract: Large language models (LLMs), and the agents built on top of them, are now benchmarked heavily on whether they can finish…
Papers 5175 stories
How Long Reasoning Chains Influence LLMs' Judgment of Answer Factuality
arXiv:2604.06756v2 Announce Type: replace Abstract: Large language models (LLMs) has been widely adopted as a scalable surrogate for human evaluation, yet such judges remain imperfect and…
Toward surface-based registration of a virtual preoperative cutting guide onto the mandible for reconstruction surgery
arXiv:2608.06599v1 Announce Type: new Abstract: Mandibular reconstruction restores facial continuity and oral function after segmental resection. Patient-specific cutting guides transfer a computed tomography (CT)-based plan to…
Symbolic Graphics Programming with Large Language Models
arXiv:2509.05208v2 Announce Type: replace-cross Abstract: Large language models (LLMs) excel at program synthesis, yet their ability to produce symbolic graphics programs (SGPs) that render into precise…
Embedded Variational Neural Stochastic Differential Equations for Learning Heterogeneous Dynamics
arXiv:2604.00669v2 Announce Type: replace Abstract: This study examines the challenges of modeling complex and noisy data related to socioeconomic factors over time, with a focus on…
Bootstrap validity in Bayesian semi-parametric models
arXiv:2608.06670v1 Announce Type: cross Abstract: We discuss Bayesian inference on a low-dimensional targeted parameter in the presence of possibly highly complex nuisance components within the semi-parametric…
Beyond Routing Weights: Faithful Response-Level Interpretation of Mixture-of-Experts Reward Models via Contribution Contrast
arXiv:2608.06400v1 Announce Type: new Abstract: Reward models are central to learning from human preferences, yet identifying what drives their predictions remains challenging. Recent sparse Mixture-of-Experts (MoE)…
Let's Unlearn Stereotypes Before Decision-Making: Assessing the Impact of Intrinsic Bias Mitigation on Downstream Fairness in LLMs
arXiv:2509.16462v2 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly used in high-stakes decision-making systems, where biased predictions can reinforce social and economic disparities. Although…
TradeVerse: A Longitudinal Benchmark of Political Negotiation in International Trade
arXiv:2608.06549v1 Announce Type: new Abstract: LLMs are increasingly being applied to tasks involving institutional and political texts, but existing benchmarks evaluate them on isolated documents or…
InsertFuse: A Unified Framework for Multi-Category Reference-Guided Image Insertion
arXiv:2608.06490v1 Announce Type: new Abstract: We present InsertFuse, a unified framework for multi-category reference-guided image insertion. Its key idea is to decouple category-specific expertise learning from…
Self-Distillation Enables Continual Learning
arXiv:2601.19897v2 Announce Type: replace Abstract: Continual learning, enabling models to acquire new skills and knowledge without degrading existing capabilities, remains a fundamental challenge for foundation models.…
Target-Weighted Neyman Allocation: Experimental Design for Heterogeneous Treatment Effects under Population Shift
arXiv:2608.06512v1 Announce Type: new Abstract: Randomized experiments are often run in one population to guide decisions in another. Allocating by experimental proportions wastes budget on groups…
Estimating and Testing Kinks in Panel Data Models
arXiv:2608.07162v1 Announce Type: cross Abstract: Many economic and financial relationships may change gradually rather than abruptly. We study panel data models in which the coefficient vector…
Cluster Attention for Graph Machine Learning
arXiv:2604.07492v2 Announce Type: replace-cross Abstract: Message Passing Neural Networks have recently become the most popular approach to graph machine learning tasks; however, their receptive field is…
Dependency Parsing Across the Resource Spectrum: Evaluating Architectures on High and Low-Resource Languages
arXiv:2605.02608v2 Announce Type: replace Abstract: Transformer-based models achieve state-of-the-art dependency parsing for high-resource languages, yet their advantage over simpler architectures in low-resource settings remains poorly understood.…
A Practical Evaluation Method for Long-Form Simultaneous Speech-to-Speech Translation
arXiv:2606.15059v2 Announce Type: replace Abstract: Simultaneous speech-to-speech translation (SimulS2ST) enables real-time cross-lingual communication, but existing evaluation has focused largely on short or pre-segmented speech rather than…
Test-Time Adaptation with Online Personalized Energy-Based Cache for Fine-Grained Video Expression Recognition
arXiv:2608.06467v1 Announce Type: new Abstract: Facial expression recognition (FER) in videos is challenging because models must identify subtle, temporally evolving affective states that vary across individuals.…
TiWeaver: Unified Temporal Dynamics Modeling via Contextual Patching
arXiv:2606.03121v2 Announce Type: replace Abstract: Multivariate time series forecasting plays a critical role in real-world applications, including weather prediction, stock analysis, and health monitoring. Due to…
CertBind from Multimodal Connectivity to Certifiable Retrieval Decisions
arXiv:2608.06516v1 Announce Type: new Abstract: Lightweight connectors make frozen multimodal encoders composable at the representation level. Deployment exposes a second problem at the level of task…
Wasserstein Mahalanobis Distances for Recovering Latent Geometry
arXiv:2608.06560v1 Announce Type: cross Abstract: The Mahalanobis distance is a fundamental covariance-adapted metric for multivariate data and plays a central role in recovering latent geometry from…
KNOWPLAN: Knowledge-Driven AI Agents for Smart Degree Pathway Planning
arXiv:2608.06530v1 Announce Type: new Abstract: Planning a degree from official university sources requires solving two problems in order. The institution's curriculum must first be reconstructed from…
GRASP: Reinforcing Language Model Anonymizers with Group Relative Policy Optimization
arXiv:2608.06526v1 Announce Type: new Abstract: Large language models can infer sensitive personal attributes, such as age, location, and occupation, from ordinary text, turning everyday writing into…
Beyond "AI Language": The case for the idiolectal nature of LLM output
arXiv:2608.06589v1 Announce Type: new Abstract: While large language model outputs are frequently analysed as a collective super variety termed "AI language," this chapter argues that this…
TransSLR: A Lightweight Transformer for Sign Language Recognition
arXiv:2608.06407v1 Announce Type: new Abstract: Automated Sign Language Recognition for under-represented languages remains a largely unsolved problem. Central African Sign Language (CASL) exemplifies this gap: the…