7 papers
Plain Transformers Can be Powerful Graph Learners
Liheng Ma, Soumyasundar Pal, Yingxue Zhang +2
Transformers have attained outstanding performance across various modalities, owing to their simple but powerful scaled-dot-product (SDP) attention mechanisms. Researchers have att…
C3PO: Optimized Large Language Model Cascades with Probabilistic Cost Constraints for Reasoning
Antonios Valkanas, Soumyasundar Pal, Pavel Rumiantsev +2
Large language models (LLMs) have achieved impressive results on complex reasoning tasks, but their high inference cost remains a major barrier to real-world deployment. A promisin…
FEval-TTC: Fair Evaluation Protocol for Test-Time Compute
Pavel Rumiantsev, Soumyasundar Pal, Yingxue Zhang +1
The performance of Large Language Models (LLMs) and the associated dollar costs of API calls can fluctuate over time, potentially invalidating conclusions drawn in prior research.…
GraphPPD: Posterior Predictive Modelling for Graph-Level Inference
Soumyasundar Pal, Liheng Ma, Amine Natik +2
Accurate modelling and quantification of predictive uncertainty is crucial in deep learning since it allows a model to make safer decisions when the data is ambiguous and facilitat…
Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs
Mohammad Ali Alomrani, Yingxue Zhang, Derek Li +14
Large language models (LLMs) have rapidly progressed into general-purpose agents capable of solving a broad spectrum of tasks. However, current models remain inefficient at reasoni…
Refining Answer Distributions for Improved Large Language Model Reasoning
Soumyasundar Pal, Didier Chételat, Yingxue Zhang +1
Large Language Models (LLMs) have exhibited an impressive capability to perform reasoning tasks, especially if they are encouraged to generate a sequence of intermediate steps. Rea…