· ai
[Paper] Heterogeneous Low-Bandwidth Pre-Training of LLMs
Pre-training large language models (LLMs) increasingly requires distributed compute, yet bandwidth constraints make it difficult to scale beyond well-provisione...
-
- · ai
[Paper] DARC: Drum accompaniment generation with fine-grained rhythm control
In music creation, rapid prototyping is essential for exploring and refining ideas, yet existing generative tools often fall short when users require both struc...
- · ai
[Paper] Meta-Learning Guided Pruning for Few-Shot Plant Pathology on Edge Devices
Farmers in remote areas need quick and reliable methods for identifying plant diseases, yet they often lack access to laboratories or high-performance computing...
- · ai
[Paper] Falcon-H1R: Pushing the Reasoning Frontiers with a Hybrid Model for Efficient Test-Time Scaling
This work introduces Falcon-H1R, a 7B-parameter reasoning-optimized model that establishes the feasibility of achieving competitive reasoning performance with s...
- · ai
[Paper] Hunting for 'Oddballs' with Machine Learning: Detecting Anomalous Exoplanets Using a Deep-Learned Low-Dimensional Representation of Transit Spectra with Autoencoders
This study explores the application of autoencoder-based machine learning techniques for anomaly detection to identify exoplanet atmospheres with unconventional...
- · ai
[Paper] Environment-Adaptive Covariate Selection: Learning When to Use Spurious Correlations for Out-of-Distribution Prediction
Out-of-distribution (OOD) prediction is often approached by restricting models to causal or invariant covariates, avoiding non-causal spurious associations that...
- · ai
[Paper] DatBench: Discriminative, Faithful, and Efficient VLM Evaluations
Empirical evaluation serves as the primary compass guiding research progress in foundation models. Despite a large body of work focused on training frontier vis...
- · ai
[Paper] Project Ariadne: A Structural Causal Framework for Auditing Faithfulness in LLM Agents
As Large Language Model (LLM) agents are increasingly tasked with high-stakes autonomous decision-making, the transparency of their reasoning processes has beco...
- · ai
[Paper] Game of Coding: Coding Theory in the Presence of Rational Adversaries, Motivated by Decentralized Machine Learning
Coding theory plays a crucial role in enabling reliable communication, storage, and computation. Classical approaches assume a worst-case adversarial model and ...
- · ai
[Paper] Placement Semantics for Distributed Deep Learning: A Systematic Framework for Analyzing Parallelism Strategies
Training large language models requires distributing computation across many accelerators, yet practitioners select parallelism strategies (data, tensor, pipeli...
- · ai
[Paper] Temporal Kolmogorov-Arnold Networks (T-KAN) for High-Frequency Limit Order Book Forecasting: Efficiency, Interpretability, and Alpha Decay
High-Frequency trading (HFT) environments are characterised by large volumes of limit order book (LOB) data, which is notoriously noisy and non-linear. Alpha de...
- · ai
[Paper] Differential Privacy for Transformer Embeddings of Text with Nonparametric Variational Information Bottleneck
We propose a privacy-preserving method for sharing text data by sharing noisy versions of their transformer embeddings. It has been shown that hidden representa...