arXiv
How Much Rank Does LoRA Need? Rank-Error Bounds for Transformer Attention
Choosing the rank of a low-rank adaptation (LoRA) update is usually an empirical task. In this paper, we provide a ta...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
$R^3$: Training Robots to Reason in Natural Language via Reinforcement Learning
Reasoning in language allows foundation models to spend more test-time compute on hard problems, such as those requir...
arXiv
Prefix Sliding for efficient test-time scaling
Test-time scaling uses extra test-time compute to improve performance, such as letting language models reason longer ...
arXiv
Gating Before Commitment: Anticipating Intent Divergence to Prevent Post-Interaction Decision Failures in Autonomous Driving
Intent misinterpretation during vehicle interactions causes recurring planning failures. We study a decision layer in...
arXiv
SwarmWorld: Stigmergic technological evolution in societies of language-model agents
Collective intelligence can emerge when individuals coordinate through a shared environment, allowing local actions t...
arXiv
ICON Decomposition: Multivariate Concept-Level Explanations of Deep Representations for Model Auditing
Deep neural networks often exploit spurious associations in their training data, a failure known as shortcut learning...
arXiv
TraceML: An Empirical Analysis of Human-Agent Planning in Machine Learning Development
Large language models write correct code for isolated problems but remain far weaker at autonomous machine-learning d...
arXiv
Planetary Prediction Engine: Autonomous Geospatial Prediction via Intelligent Data Selection and Foundation Model Embeddings
Addressing critical global challenges, from food security and disaster risk to disease outbreaks and socio-economic v...
arXiv
Finding and using interpretable latents in a neutrino foundation model with sparse autoencoders
We present a first application of sparse-autoencoder-based mechanistic interpretability to particle physics. Studying...
arXiv
MyoMechanix: Biomechanically-Grounded Compositional Skilled Activity Understanding and Coaching
Existing action quality assessment (AQA) datasets and methods rely primarily on visual inputs such as RGB and pose, o...
arXiv
A Visual Dependence-Aware Framework for Multimodal Unsupervised Continual Post-Training
In this paper, we explore a novel task of Multimodal Unsupervised Continual Post-Training (MU-CPT), enabling deployed...
arXiv
VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning
Native visual reasoning treats visual generation as the medium of reasoning itself: visual states (i.e. images and vi...