· ai
[Paper] The Confidence Trap: Gender Bias and Predictive Certainty in LLMs
The increased use of Large Language Models (LLMs) in sensitive domains leads to growing interest in how their confidence scores correspond to fairness and bias....
-
- · ai
[Paper] Kinship Data Benchmark for Multi-hop Reasoning
Large language models (LLMs) are increasingly evaluated on their ability to perform multi-hop reasoning, i.e., to combine multiple pieces of information into a ...
- · ai
[Paper] Benchmarking Small Language Models and Small Reasoning Language Models on System Log Severity Classification
System logs are crucial for monitoring and diagnosing modern computing infrastructure, but their scale and complexity require reliable and efficient automated i...
- · ai
[Paper] Beyond Single-Shot: Multi-step Tool Retrieval via Query Planning
LLM agents operating over massive, dynamic tool libraries rely on effective retrieval, yet standard single-shot dense retrievers struggle with complex requests....
- · ai
[Paper] OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agent
While Vision-Language Models (VLMs) have significantly advanced Computer-Using Agents (CUAs), current frameworks struggle with robustness in long-horizon workfl...
- · ai
[Paper] DT-ICU: Towards Explainable Digital Twins for ICU Patient Monitoring via Multi-Modal and Multi-Task Iterative Inference
We introduce DT-ICU, a multimodal digital twin framework for continuous risk estimation in intensive care. DT-ICU integrates variable-length clinical time serie...
- · ai
[Paper] Are LLM Decisions Faithful to Verbal Confidence?
Large Language Models (LLMs) can produce surprisingly sophisticated estimates of their own uncertainty. However, it remains unclear to what extent this expresse...
- · ai
[Paper] Free-RBF-KAN: Kolmogorov-Arnold Networks with Adaptive Radial Basis Functions for Efficient Function Learning
Kolmogorov-Arnold Networks (KANs) have shown strong potential for efficiently approximating complex nonlinear functions. However, the original KAN formulation r...
- · ai
[Paper] Learning to bin: differentiable and Bayesian optimization for multi-dimensional discriminants in high-energy physics
Categorizing events using discriminant observables is central to many high-energy physics analyses. Yet, bin boundaries are often chosen by hand. A simple, popu...
- · ai
[Paper] Riesz Representer Fitting under Bregman Divergence: A Unified Framework for Debiased Machine Learning
Estimating the Riesz representer is a central problem in debiased machine learning for causal and structural parameter estimation. Various methods for Riesz rep...
- · ai
[Paper] Improving Domain Generalization in Contrastive Learning using Adaptive Temperature Control
Self-supervised pre-training with contrastive learning is a powerful method for learning from sparsely labeled data. However, performance can drop considerably ...
- · ai
[Paper] Evaluating the encoding competence of visual language models using uncommon actions
We propose UAIT (Uncommon-sense Action Image-Text) dataset, a new evaluation benchmark designed to test the semantic understanding ability of visual language mo...