Search Results for author:
Found 4 papers, 2 papers with code
Frugal LMs Trained to Invoke Symbolic Solvers Achieve Parameter-Efficient Arithmetic Reasoning
In this paper, we start with the hypothesis that much smaller LMs, which are weak at multi-step reasoning, can achieve reasonable arithmetic reasoning if arithmetic word problems are posed as a formalize-then-solve task.
Ranked #11 on
Math Word Problem Solving
on SVAMP
(using extra training data)
IDD-AW: A Benchmark for Safe and Robust Segmentation of Drive Scenes in Unstructured Traffic and Adverse Weather
larger label set with a 4-level label hierarchy to capture unstructured traffic conditions.
Small Language Models Fine-tuned to Coordinate Larger Language Models improve Complex Reasoning
Additionally, we show that DaSLaM is not limited by the solver's capabilities as a function of scale; e. g., solver LMs with diverse sizes give significant performance improvement with our solver-agnostic decomposition technique.
Ranked #6 on
Overall - Test
on JEEBench
(using extra training data)
Semantic Map Injected GAN Training for Image-to-Image Translation
Specifically, we train with original input and output modalities and inject a few epochs of training for translation from input to semantic map.
Generative Adversarial Network
Image-to-Image Translation
+2
