Dan Roth

Log-Augmented Generation: Scaling Test-Time Reasoning with Reusable Computation

Learning Human-Perceived Fakeness in AI-Generated Videos via Multimodal LLMs

CONCUR: A Framework for Continual Constrained and Unconstrained Routing

Demystifying Supervision Data Generalization in Multimodal LMs

RAG Makes Guardrails Unsafe? Investigating Robustness of Guardrails under RAG-style Contexts

On Improving Neurosymbolic Learning by Exploiting the Representation Space

Tree-based Dialogue Reinforced Policy Optimization for Red-Teaming Attacks

Routesplain: Towards Faithful and Intervenable Routing for Software-related Tasks

Optimizable LLM Planning: A Branch-and-Bound Framework for Complex Tasks

Polynomial-Time Reasoning at the Edge of NP

BIRD: A Trustworthy Bayesian Inference Framework for Large Language Models

Imbalances in Neurosymbolic Learning: Characterization and Mitigating Strategies

EnrichIndex: Using LLMs to Enrich Retrieval Indices Offline

Beyond correlation: The impact of human uncertainty in measuring the effectiveness of automatic evaluation and LLM-as-a-judge

Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale

GIVE: Structured Reasoning of Large Language Models with Knowledge Graph Inspired Veracity Extrapolation

GIVE: Structured Reasoning with Knowledge Graph Inspired Veracity Extrapolation

ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding

Aligning to Constraints for Data-Efficient Language Model Customization

MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding

On Characterizing and Mitigating Imbalances in Multi-Instance Partial Label Learning

Model Tells Itself Where to Attend: Steerable Prompting for Reliable Reading Comprehension of LLM

DiverseAgentEntropy: Quantifying Black-Box LLM Uncertainty through Diverse Perspectives and Multi-Agent Interaction