6.1k citations · 6.3k across the 31 of their papers we have counts for
8 papers · 1 filter
Small Vocabularies, Big Gains: Pretraining and Tokenization in Time Series Models
Alexis Roger, Gwen Legate, Kashif Rasul +2
Tokenization and transfer learning are two critical components in building state of the art time series foundation models for forecasting. In this work, we systematically study the…
Understanding the Mixture-of-Experts with Nadaraya-Watson Kernel
Chuanyang Zheng, Jiankai Sun, Yihang Gao +13
Mixture-of-Experts (MoE) has become a cornerstone in recent state-of-the-art large language models (LLMs). Traditionally, MoE relies on as the router score funct…
Chart-RVR: Reinforcement Learning with Verifiable Rewards for Explainable Chart Reasoning
Sanchit Sinha, Oana Frunza, Kashif Rasul +2
The capabilities of Large Vision-Language Models (LVLMs) have reached state-of-the-art on many visual reasoning tasks, including chart reasoning, yet they still falter on out-of-di…
Improving Reasoning for Diffusion Language Models via Group Diffusion Policy Optimization
Kevin Rojas, Jiahe Lin, Kashif Rasul +4
Diffusion language models (DLMs) enable parallel, order-agnostic generation with iterative refinement, offering a flexible alternative to autoregressive large language models (LLMs…
Random Initialization Can't Catch Up: The Advantage of Language Model Transfer for Time Series Forecasting
Roland Riachi, Kashif Rasul, Arjun Ashok +5
Recent works have demonstrated the effectiveness of adapting pre-trained language models (LMs) for forecasting time series in the low-data regime. We build upon these findings by a…
Proximal Point Nash Learning from Human Feedback
Daniil Tiapkin, Daniele Calandriello, Denis Belomestny +5
Traditional Reinforcement Learning from Human Feedback (RLHF) often relies on reward models, frequently assuming preference structures like the Bradley--Terry model, which may not…