Picture for Subbarao Kambhampati

Subbarao Kambhampati

Mind The Gap: Deep Learning Doesn't Learn Deeply

Add code
May 24, 2025
Viaarxiv icon

Interpretable Traces, Unexpected Outcomes: Investigating the Disconnect in Trace-Based Knowledge Distillation

Add code
May 20, 2025
Viaarxiv icon

Beyond Semantics: The Unreasonable Effectiveness of Reasonless Intermediate Tokens

Add code
May 19, 2025
Viaarxiv icon

RL in Name Only? Analyzing the Structural Assumptions in RL post-training for LLMs

Add code
May 19, 2025
Viaarxiv icon

(How) Do reasoning models reason?

Add code
Apr 14, 2025
Viaarxiv icon

Who is Helping Whom? Analyzing Inter-dependencies to Evaluate Cooperation in Human-AI Teaming

Add code
Feb 10, 2025
Viaarxiv icon

Robust Planning with Compound LLM Architectures: An LLM-Modulo Approach

Add code
Nov 20, 2024
Viaarxiv icon

Planning in Strawberry Fields: Evaluating and Improving the Planning and Scheduling Capabilities of LRM o1

Add code
Oct 03, 2024
Figure 1 for Planning in Strawberry Fields: Evaluating and Improving the Planning and Scheduling Capabilities of LRM o1
Figure 2 for Planning in Strawberry Fields: Evaluating and Improving the Planning and Scheduling Capabilities of LRM o1
Figure 3 for Planning in Strawberry Fields: Evaluating and Improving the Planning and Scheduling Capabilities of LRM o1
Figure 4 for Planning in Strawberry Fields: Evaluating and Improving the Planning and Scheduling Capabilities of LRM o1
Viaarxiv icon

Algorithmic Language Models with Neurally Compiled Libraries

Add code
Jul 06, 2024
Viaarxiv icon

Robust Planning with LLM-Modulo Framework: Case Study in Travel Planning

Add code
May 31, 2024
Viaarxiv icon