Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2607. 16705v1 Announce Type: cross Abstract: Semi-supervised learning (SSL) is an effective solution for medical image segmentation with limited annotations.
arXiv:2607. 17686v1 Announce Type: cross Abstract: Modern software teams have mature tools for low-level testing, such as pytest, JUnit, and Jest, which make it inexpensive to write unit tests and run them on every commit.
arXiv:2607. 17266v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated remarkable capabilities in natural language processing.
arXiv:2607. 17674v1 Announce Type: cross Abstract: A language model $p_\theta(y \mid x)$ trained on reasoning tasks learns to solve problems via multiple distinct strategies, yet these strategies are implicit and entangled within the model's response distribution.
arXiv:2607. 16286v1 Announce Type: cross Abstract: The 3D geometry of real-world scene data is often incomplete.
arXiv:2607. 16682v1 Announce Type: cross Abstract: The widespread adoption of high-level deep learning libraries, while accelerating model development, has increasingly abstracted away the internal mechanics of neural networks, creating a gap between practical usage and fundamental understanding.
arXiv:2607. 18130v1 Announce Type: new Abstract: Most parameter-efficient finetuning (PEFT) methods adapt weights or activations, thus leaving one of the key Transformer components unchanged: residual connections.
arXiv:2607. 17762v1 Announce Type: cross Abstract: Large language model (LLM)-driven evolutionary search is an emerging algorithm-discovery paradigm that has already produced novel results in several scientific fields.
arXiv:2503. 08245v4 Announce Type: replace Abstract: In mixed graphs, there are both directed and bidirected edges.
arXiv:2510. 27497v2 Announce Type: replace-cross Abstract: Transformer-based autoregressive models have emerged as a unifying paradigm across modalities such as text and images, but their extension to 3D molecule generation remains underexplored.
arXiv:2603. 29219v2 Announce Type: replace-cross Abstract: Sign language is the primary approach of communication for the Deaf and Hard-of-Hearing (DHH) community.
arXiv:2603. 13065v2 Announce Type: replace-cross Abstract: Deep learning models achieve high accuracy in time series classification, yet understanding their class-level decision behaviour remains challenging.
arXiv:2602. 05463v2 Announce Type: replace-cross Abstract: Modern AI systems achieve remarkable capabilities at the cost of substantial energy consumption.
arXiv:2607. 17842v1 Announce Type: cross Abstract: Recent breakthroughs in 3D Gaussian Splatting (3DGS) have advanced neural rendering with high fidelity and speed.
arXiv:2607. 16736v1 Announce Type: cross Abstract: This paper presents RealDESED, a real-world domestic sound event detection (SED) benchmark comprising 5,710 audio recordings collected by 652 participants in their homes.
arXiv:2607. 16685v1 Announce Type: cross Abstract: Conditional diffusion models have become a powerful and flexible framework for learning complex conditional distributions from labeled data.
arXiv:2607. 18199v1 Announce Type: cross Abstract: Not all training samples contribute equally to large language model fine-tuning.
Large language models (LLMs) increasingly support science, but they can also convert hazardous scientific knowledge into actionable misuse guidance. Existing benchmarks often rely on templated queries disconnected from real-world hazards, and employ LLM-as-a-Judge paradigms without domain grounding.
Safety interventions on dual-use knowledge typically choose between destroying hazardous content (e. g.
Multi-vector dense retrieval models, such as ColBERT, achieve strong retrieval effectiveness by modelling fine-grained token-level interactions between queries and documents. Methods such as PLAID use centroid-based quantisation of each token's vector to reduce the index size and speed up retrieval while maintaining strong effectiveness.