Saravan Rajmohan

Learning GUI Grounding with Spatial Reasoning from Visual Feedback

ACTS: Adaptive Control for Test-time Scaling

Multi-Preference Optimization: Generalizing DPO via Set-Level Contrasts

Towards Active Synthetic Data Generation for Finetuning Language Models

OdysseyBench: Evaluating LLM Agents on Long-Horizon Complex Office Application Workflows

Simulating Environments with Large Language Models for Generic Agent Training

REFA: Reference Free Alignment with Fine-Grained Length Control

RuAG: Learned-rule-augmented Generation for Large Language Models

Thread: A Logic-Based Data Organization Paradigm for How-To Question Answering with Retrieval Augmented Generation

Minerva: A Programmable Memory Test Benchmark for Language Models

Exploring How LLMs Capture and Represent Domain-Specific Knowledge

AMPO: Active Multi Preference Optimization for Self-play Preference Selection

Zoomer: Enhancing MLLM Performance with Adaptive Image Focus Optimization