papers

Publications (10)

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.CL2025

Measuring what Matters: Construct Validity in Large Language Model Benchmarks

Andrew M. Bean, Ryan Othniel Kearns, Angelika Romanou +39

Evaluating large language models (LLMs) is crucial for both assessing their capabilities and identifying safety or robustness issues prior to deployment. Reliably measuring abstrac…

cs.CL2025

Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought

James Chua, Edward Rees, Hunar Batra +4

Chain-of-thought prompting (CoT) has the potential to improve the explainability of language model reasoning. But CoT can also systematically misrepresent the factors influencing m…

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.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…

#alignment#midtraining#large language models#constitutional AI
cs.LG2026

Humanity's Last Exam

Long Phan, Alice Gatti, Ziwen Han +1144

Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achi…

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…

cs.LG2024

EVCL: Elastic Variational Continual Learning with Weight Consolidation

Hunar Batra, Ronald Clark

Continual learning aims to allow models to learn new tasks without forgetting what has been learned before. This work introduces Elastic Variational Continual Learning with Weight…

cs.CV2026

Towards Understanding Multimodal Fine-Tuning: Spatial Features

Lachin Naghashyar, Hunar Batra, Ashkan Khakzar +4

Contemporary Vision-Language Models (VLMs) achieve strong performance on a wide range of tasks by pairing a vision encoder with a pre-trained language model, fine-tuned for visual-…