6 papers
UWM-JEPA: Predictive World Models That Imagine in Belief Space
Santosh Kumar Radha, Oktay Goktas
World models for partially observed environments must imagine multiple compatible hidden futures and steer between them under counterfactual actions. Joint Embedding Predictive Arc…
Improving BM25 Code Retrieval Under Fixed Generic Tokenization: Adaptive q-Log Odds as a Drop-In BM25 Fix
Santosh Kumar Radha, Oktay Goktas
In retrieval-augmented coding, failures often begin when the relevant file is absent from the retrieved context. Under frozen generic tokenization, where a BM25 index has been buil…
Adaptive Graph of Thoughts: Test-Time Adaptive Reasoning Unifying Chain, Tree, and Graph Structures
Tushar Pandey, Ara Ghukasyan, Oktay Goktas +1
Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, yet their performance is highly dependent on the prompting strategy and model scale. While reinfor…
On the Reasoning Capacity of AI Models and How to Quantify It
Santosh Kumar Radha, Oktay Goktas
Recent advances in Large Language Models (LLMs) have intensified the debate surrounding the fundamental nature of their reasoning capabilities. While achieving high performance on…
Composite Learning Units: Generalized Learning Beyond Parameter Updates to Transform LLMs into Adaptive Reasoners
Santosh Kumar Radha, Oktay Goktas
Human learning thrives on the ability to learn from mistakes, adapt through feedback, and refine understanding-processes often missing in static machine learning models. In this wo…
Iteration of Thought: Leveraging Inner Dialogue for Autonomous Large Language Model Reasoning
Santosh Kumar Radha, Yasamin Nouri Jelyani, Ara Ghukasyan +1
Iterative human engagement is a common and effective means of leveraging the advanced language processing power of large language models (LLMs). Using well-structured prompts in a…