Related papers: THEIA: Learning Complete Kleene Three-Valued Logic…

Deep learning models trained to optimize average accuracy often exhibit systematic failures on particular subpopulations. In real world settings, the subpopulations most affected by such disparities are frequently unlabeled or unknown,…

Purpose: to assess the efficacy of THEIA, an artificial intelligence for screening diabetic retinopathy in a multi-center prospective study. To validate the potential application of THEIA as clinical decision making assistant in a national…

Low-Rank Adaptation (LoRA) has become the dominant parameter-efficient fine-tuning method for large language models, yet standard practice applies LoRA adapters uniformly to all transformer layers regardless of their relevance to the…

We present a novel multi-stage workflow for computational materials discovery that achieves a 99% success rate in identifying compounds within 100 meV/atom of thermodynamic stability, with a threefold improvement over previous approaches.…

Continual Learning (CL) empowers AI models to continuously learn from sequential task streams. Recently, parameter-efficient fine-tuning (PEFT)-based CL methods have garnered increasing attention due to their superior performance. They…

Deep Learning (DL) is a class of machine learning algorithms that are used in a wide variety of applications. Like any software system, DL programs can have bugs. To support bug localization in DL programs, several tools have been proposed…

This paper asks whether a bounded neural architecture can exhibit a meaningful division of labor between intuition and deliberation on a classic 64-item syllogistic reasoning benchmark. More broadly, the benchmark is relevant to ongoing…

World models have enabled interactive exploration of game environments and robotic manipulation, but physical engineering remains beyond their reach: real materials exhibit nonlinear constitutive laws, carry history-dependent internal…

Large language models (LLMs) have demonstrated technical accuracy in high-risk domains, such as mental health support and special education. However, they often fail to meet the nuanced behavioral expectations of domain experts. This gap…

Entity Alignment (EA) aims to find equivalent entity pairs between KGs, which is the core step of bridging and integrating multi-source KGs. In this paper, we argue that existing GNN-based EA methods inherit the inborn defects from their…

Large language models run every token through every layer, regardless of difficulty. We present TIDE, a post-training system that attaches tiny learned routers at periodic checkpoint layers and, at inference time, selects the earliest layer…

Embedding-based entity alignment (EEA) has recently received great attention. Despite significant performance improvement, few efforts have been paid to facilitate understanding of EEA methods. Most existing studies rest on the assumption…

Conditional depth execution routes a subset of tokens through a lightweight cheap FFN while the remainder execute the standard full FFN at each controlled layer. The central difficulty is gate training: the gate decision must propagate…

LLM-based universal information extraction (UIE) methods often rely on additional information beyond the original training data, which increases training complexity yet often yields limited gains. To address this, we propose ProUIE, a…

For any positive integer $k$, there exist neural networks with $\Theta(k^3)$ layers, $\Theta(1)$ nodes per layer, and $\Theta(1)$ distinct parameters which can not be approximated by networks with $\mathcal{O}(k)$ layers unless they are…

Most deep learning recommendation models operate as black boxes, relying on latent representations that obscure their decision process. This lack of intrinsic interpretability raises concerns in applications that require transparency and…

This work investigates neural algorithmic reasoning to develop neural networks capable of learning from classical algorithms. The main challenge is to develop graph neural networks that are expressive enough to predict the given algorithm…

Transfer learning with pre-training on large-scale datasets has played an increasingly significant role in computer vision and natural language processing recently. However, as there exist numerous application scenarios that have…

Do neural networks learn to implement algorithms such as look-ahead or search "in the wild"? Or do they rely purely on collections of simple heuristics? We present evidence of learned look-ahead in the policy network of Leela Chess Zero,…

The escalating demand for efficient decoding in large language models (LLMs) is particularly critical for reasoning-intensive architectures like OpenAI-o3 and DeepSeek-R1, which depend on extended chain-of-thought reasoning. This study…