works on

From the 1 of 9 linked papers with an AI index.

collaborators

9 papers

cs.CV2026

Multimodal Model Diffing for Feature Discovery and Control

Hunar Batra, Lachin Naghashyar, Ashkan Khakzar +4

Multimodal Large Language Models (MLLMs) exhibit strong visual understanding, yet the internal features that cause these behaviors remain difficult to identify, audit, or control.…

cs.CL2026

Constitutional Midtraining: Content Presence Drives Alignment Gains

Desiree Cho, Cameron Tice, Bernie Hogan +4

The paper investigates inserting constitutionally‑derived content during midtraining of large language models to improve the durability of alignment, showing reduced blackmail tend…

cs.CL2026

Reasoning Fine-Tuning Induces Persistent Latent Policy States

Abir Harrasse, Michael Lan, Hunar Batra +2

Reasoning-specialized language models show large performance gains over base models, yet the internal changes responsible for improved multi-step reasoning remain poorly understood…

cs.CV2026

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards

Hunar Batra, Haoqin Tu, Hardy Chen +3

Multimodal large language models (MLLMs) have achieved remarkable progress in vision-language tasks, but continue to struggle with spatial reasoning. Existing spatial MLLMs rely on…

cs.CL2026

MCJudgeBench: A Benchmark for Constraint-Level Judge Evaluation in Multi-Constraint Instruction Following

Jaeyun Lee, Junyoung Koh, Zeynel Tok +2

Multi-constraint instruction following requires verifying whether a response satisfies multiple individual requirements, yet LLM judges are often assessed only through overall-resp…

cs.CL2026

Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks

Benjamin Warner, Ratna Sagari Grandhi, Max Kieffer +32

Evaluating large language models (LLMs) for medical applications remains challenging due to benchmark saturation, limited data accessibility, and insufficient coverage of relevant…