Caravan MultiMet: Extending Caravan with Multiple Weather Nowcasts and Forecasts
By Kate Martin
Posted on: November 15, 2024
The Caravan large-sample hydrology dataset (Kratzert et al., 2023) was created to standardize and harmonize streamflow data from various regional datasets, combined with globally available meteorological forcing and catchment attributes. This community-driven project also allows researchers to conve...
Scaling Mesh Generation via Compressive Tokenization
By Kate Martin
Posted on: November 13, 2024
We propose a compressive yet effective mesh representation, Blocked and Patchified Tokenization (BPT), facilitating the generation of meshes exceeding 8k faces. BPT compresses mesh sequences by employing block-wise indexing and patch aggregation, reducing their length by approximately 75\% compared ...
The Surprising Effectiveness of Test-Time Training for Abstract Reasoning
By Naomi Wilson
Posted on: November 13, 2024
Language models have shown impressive performance on tasks within their training distribution, but often struggle with novel problems requiring complex reasoning. We investigate the effectiveness of test-time training (TTT) -- updating model parameters temporarily during inference using a loss deriv...
CDXFormer: Boosting Remote Sensing Change Detection with Extended Long Short-Term Memory
By Kate Martin
Posted on: November 13, 2024
In complex scenes and varied conditions, effectively integrating spatial-temporal context is crucial for accurately identifying changes. However, current RS-CD methods lack a balanced consideration of performance and efficiency. CNNs lack global context, Transformers have quadratic computational com...
Recent research on the 1-bit Large Language Models (LLMs), such as BitNet b1.58, presents a promising direction for reducing the inference cost of LLMs while maintaining their performance. In this work, we introduce BitNet a4.8, enabling 4-bit activations for 1-bit LLMs. BitNet a4.8 employs a hybrid...
Enhancing Investment Analysis: Optimizing AI-Agent Collaboration in Financial Research
By Naomi Wilson
Posted on: November 11, 2024
In recent years, the application of generative artificial intelligence (GenAI) in financial analysis and investment decision-making has gained significant attention. However, most existing approaches rely on single-agent systems, which fail to fully utilize the collaborative potential of multiple AI...
MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views
By Javier Vásquez
Posted on: November 11, 2024
We introduce MVSplat360, a feed-forward approach for 360{\deg} novel view synthesis (NVS) of diverse real-world scenes, using only sparse observations. This setting is inherently ill-posed due to minimal overlap among input views and insufficient visual information provided, making it challenging fo...
With the increasing inference cost of machine learning models, there is a growing interest in models with fast and efficient inference. Recently, an approach for learning logic gate networks directly via a differentiable relaxation was proposed. Logic gate networks are faster than conventional neura...
