Deepanway Ghosal

Test-Time Scaling via Error Localization

Rajiv Shailesh Chitale, Rahul Madhavan, Tanisha Gupta, Deepanway Ghosal et autres

Scaling inference-time computation has emerged as a reliable method to improve the performance of large language models on complex reasoning and programming tasks. However, standard approaches such as independent sampling and sequential multi-turn refinement operate without token-level credit assignment, resulting in computational …

Test-Time Scaling via Error Localization

Rajiv Shailesh Chitale, Rahul Madhavan, Tanisha Gupta, Deepanway Ghosal et autres

Scaling inference-time computation has emerged as a reliable method to improve the performance of large language models on complex reasoning and programming tasks. However, standard approaches such as independent sampling and sequential multi-turn refinement operate without token-level credit assignment, resulting in computational …

The FACTS Leaderboard: A Comprehensive Benchmark for Large Language Model Factuality

An Chung Cheng, Alon Jacovi, Amir Globerson, Ben Golan et autres

We introduce The FACTS Leaderboard, an online leaderboard suite and associated set of benchmarks that comprehensively evaluates the ability of language models to generate factually accurate text across diverse scenarios. The suite provides a holistic measure of factuality by aggregating the performance …

Discovering the complete enhancer map of human herpesviruses using a natural language processing model

Nilabja Roy Chowdhury, Deepanway Ghosal, Vyacheslav Gurevich, Meir Shamay

Enhancers are distal cis-regulatory elements that dictate complex transcriptional repertoire. Herpes viruses exhibit programmed latent and lytic gene expression depending on the infected tissue and physiological state. Previously, using a systematic functional assay, we identified six enhancers within the genome of Kaposi’s …

il (code pays fourni par la source)

The Jumping Reasoning Curve? Tracking the Evolution of Reasoning Performance in GPT-[n] and o-[n] Models on Multimodal Puzzles

Vernon Toh, Yew Ken Chia, Deepanway Ghosal, Soujanya Poria

The releases of OpenAI's o-[n] series, such as o1, o3, and o4-mini, mark a significant paradigm shift in Large Language Models towards advanced reasoning capabilities. Notably, models like o3 have demonstrated strong performance on benchmarks like the Abstraction and Reasoning Corpus for …

AlgoPuzzleVQA: Diagnosing Multimodal Reasoning Challenges of Language Models with Algorithmic Multimodal Puzzles

Deepanway Ghosal, Vernon Toh, Yew Ken Chia, Soujanya Poria

Deepanway Ghosal, Vernon Toh, Yew Ken Chia, Soujanya Poria. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

sg (code pays fourni par la source)

Evaluating LLMs’ Mathematical and Coding Competency through Ontology-guided Interventions

Pengfei Hong, Navonil Majumder, Deepanway Ghosal, Somak Aditya et autres

Recent advancements in Large Language Models (LLMs) have showcased striking results on existing logical reasoning benchmarks, with some models even surpassing human performance.However, the true depth of their competencies and robustness in reasoning tasks remains an open question.To this end, in this …

Égypte, sg, in, us (code pays fourni par la source)

Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning

Qi Sun, Pengfei Hong, Tej Deep Pala, Vernon Toh et autres

NLKI: A Lightweight Natural Language Knowledge Integration Framework for Improving Small VLMs in Commonsense VQA Tasks

Aritra Dutta, Swapnanil Mukherjee, Deepanway Ghosal, Somak Aditya

Commonsense visual-question answering often hinges on knowledge that is missing from the image or the question.Small visionlanguage models (sVLMs) such as ViLT, Visu-alBERT and FLAVA therefore lag behind their larger generative counterparts.To study the effect of careful commonsense knowledge integration on sVLMs, …

in (code pays fourni par la source)

Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning

Qi Sun, Pengfei Hong, Tej Deep Pala, Vernon Toh et autres

Traditional reinforcement learning-based robotic control methods are often task-specific and fail to generalize across diverse environments or unseen objects and instructions. Visual Language Models (VLMs) demonstrate strong scene understanding and planning capabilities but lack the ability to generate actionable policies tailored to …

Tango 2: Aligning Diffusion-based Text-to-Audio Generations through Direct Preference Optimization

Navonil Majumder, Chia-Yu Hung, Deepanway Ghosal, Wei-Ning Hsu et autres

Peer Reviewed

sg, us (code pays fourni par la source)

MixEval-X: Any-to-Any Evaluations from Real-World Data Mixtures

Jinjie Ni, Yifan Song, Deepanway Ghosal, Bo Li et autres

Perceiving and generating diverse modalities are crucial for AI models to effectively learn from and engage with real-world signals, necessitating reliable evaluations for their development. We identify two major issues in current evaluations: (1) inconsistent standards, shaped by different communities with varying …