· ai
[Paper] Predictive Safety Shield for Dyna-Q Reinforcement Learning
Obtaining safety guarantees for reinforcement learning is a major challenge to achieve applicability for real-world tasks. Safety shields extend standard reinfo...
-
- · ai
[Paper] The Age-specific Alzheimer 's Disease Prediction with Characteristic Constraints in Nonuniform Time Span
Alzheimer's disease is a debilitating disorder marked by a decline in cognitive function. Timely identification of the disease is essential for the development ...
- · ai
[Paper] Phase Transition for Stochastic Block Model with more than sqrt(n) Communities (II)
A fundamental theoretical question in network analysis is to determine under which conditions community recovery is possible in polynomial time in the Stochasti...
- · ai
[Paper] EoS-FM: Can an Ensemble of Specialist Models act as a Generalist Feature Extractor?
Recent advances in foundation models have shown great promise in domains such as natural language processing and computer vision, and similar efforts are now em...
- · ai
[Paper] Pessimistic Verification for Open Ended Math Questions
The key limitation of the verification performance lies in the ability of error detection. With this intuition we designed several variants of pessimistic verif...
- · ai
[Paper] Self-Paced Learning for Images of Antinuclear Antibodies
Antinuclear antibody (ANA) testing is a crucial method for diagnosing autoimmune disorders, including lupus, Sjögren's syndrome, and scleroderma. Despite its im...
- · ai
[Paper] Voice, Bias, and Coreference: An Interpretability Study of Gender in Speech Translation
Unlike text, speech conveys information about the speaker, such as gender, through acoustic cues like pitch. This gives rise to modality-specific bias concerns....
- · ai
[Paper] Mechanistic Interpretability for Transformer-based Time Series Classification
Transformer-based models have become state-of-the-art tools in various machine learning tasks, including time series classification, yet their complexity makes ...
- · ai
[Paper] IntAttention: A Fully Integer Attention Pipeline for Efficient Edge Inference
Deploying Transformer models on edge devices is limited by latency and energy budgets. While INT8 quantization effectively accelerates the primary matrix multip...
- · ai
[Paper] Tool-RoCo: An Agent-as-Tool Self-organization Large Language Model Benchmark in Multi-robot Cooperation
This study proposes Tool-RoCo, a novel benchmark for evaluating large language models (LLMs) in long-term multi-agent cooperation based on RoCo, a multi-robot c...
- · ai
[Paper] Generalized Design Choices for Deepfake Detectors
The effectiveness of deepfake detection methods often depends less on their core design and more on implementation details such as data preprocessing, augmentat...
- · ai
[Paper] CanKD: Cross-Attention-based Non-local operation for Feature-based Knowledge Distillation
We propose Cross-Attention-based Non-local Knowledge Distillation (CanKD), a novel feature-based knowledge distillation framework that leverages cross-attention...