· ai
[Paper] FrontierCS: Evolving Challenges for Evolving Intelligence
We introduce FrontierCS, a benchmark of 156 open-ended problems across diverse areas of computer science, designed and reviewed by experts, including CS PhDs an...
-
- · ai
[Paper] mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs
Prevailing Vision-Language-Action Models (VLAs) for robotic manipulation are built upon vision-language backbones pretrained on large-scale, but disconnected st...
- · ai
[Paper] Multi-Modal Semantic Communication
Semantic communication aims to transmit information most relevant to a task rather than raw data, offering significant gains in communication efficiency for app...
- · ai
[Paper] BashArena: A Control Setting for Highly Privileged AI Agents
Future AI agents might run autonomously with elevated privileges. If these agents are misaligned, they might abuse these privileges to cause serious damage. The...
- · ai
[Paper] Can LLMs Guide Their Own Exploration? Gradient-Guided Reinforcement Learning for LLM Reasoning
Reinforcement learning has become essential for strengthening the reasoning abilities of large language models, yet current exploration mechanisms remain fundam...
- · ai
[Paper] A Multivariate Statistical Framework for Detection, Classification and Pre-localization of Anomalies in Water Distribution Networks
This paper presents a unified framework, for the detection, classification, and preliminary localization of anomalies in water distribution networks using multi...
- · ai
[Paper] High-Dimensional Partial Least Squares: Spectral Analysis and Fundamental Limitations
Partial Least Squares (PLS) is a widely used method for data integration, designed to extract latent components shared across paired high-dimensional datasets. ...
- · ai
[Paper] Stylized Synthetic Augmentation further improves Corruption Robustness
This paper proposes a training data augmentation pipeline that combines synthetic image data with neural style transfer in order to address the vulnerability of...
- · ai
[Paper] Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers
Large language model (LLM) activations are notoriously difficult to understand, with most existing techniques using complex, specialized methods for interpretin...
- · ai
[Paper] Explaining the Reasoning of Large Language Models Using Attribution Graphs
Large language models (LLMs) exhibit remarkable capabilities, yet their reasoning remains opaque, raising safety and trust concerns. Attribution methods, which ...
- · ai
[Paper] Stepwise Think-Critique: A Unified Framework for Robust and Interpretable LLM Reasoning
Human beings solve complex problems through critical thinking, where reasoning and evaluation are intertwined to converge toward correct solutions. However, mos...
- · ai
[Paper] PPSEBM: An Energy-Based Model with Progressive Parameter Selection for Continual Learning
Continual learning remains a fundamental challenge in machine learning, requiring models to learn from a stream of tasks without forgetting previously acquired ...