Search Results for author:
Found 10 papers, 3 papers with code
Predicting Through Generation: Why Generation Is Better for Prediction
This paper argues that generating output tokens is more effective than using pooled representations for prediction tasks because token-level generation retains more mutual information.
TituLLMs: A Family of Bangla LLMs with Comprehensive Benchmarking
There was a lack of benchmarking datasets to evaluate LLMs for Bangla.
User Profile with Large Language Models: Construction, Updating, and Benchmarking
In this paper, we present two high-quality open-source user profile datasets: one for profile construction and another for profile updating.
Does Self-Attention Need Separate Weights in Transformers?
The success of self-attention lies in its ability to capture long-range dependencies and enhance context understanding, but it is limited by its computational complexity and challenges in handling sequential data with inherent directionality.
LLM-Mixer: Multiscale Mixing in LLMs for Time Series Forecasting
Time series forecasting remains a challenging task, particularly in the context of complex multiscale temporal patterns.
RoCoFT: Efficient Finetuning of Large Language Models with Row-Column Updates
We propose RoCoFT, a parameter-efficient fine-tuning method for large-scale language models (LMs) based on updating only a few rows and columns of the weight matrices in transformers.
Parameter-Efficient Fine-Tuning of Large Language Models using Semantic Knowledge Tuning
This method involves using a fixed LLM to understand and process the semantic content of the prompt through zero-shot capabilities.
Propulsion: Steering LLM with Tiny Fine-Tuning
The rapid advancements in Large Language Models (LLMs) have revolutionized natural language processing (NLP) and related fields.
Changes by Butterflies: Farsighted Forecasting with Group Reservoir Transformer
We introduce Group Reservoir Transformer to predict long-term events more accurately and robustly by overcoming two challenges in Chaos: (1) the extensive historical sequences and (2) the sensitivity to initial conditions.
Impact Learning: A Learning Method from Features Impact and Competition
This algorithm is remarkable for learning from the competitive situation and the competition comes from the effects of autonomous features.
