Papers by Ranjay Krishna

10 papers
DreamSync: Aligning Text-to-Image Generation with Image Understanding Feedback (2025.naacl-long)

Copied to clipboard

Challenge: Text-to-Image models (T2I) still struggle to produce images that are both aesthetically pleasing and faithful to the user’s input text.
Approach: They propose a training algorithm that trains T2I models to be faithful to the input text.
Outcome: The proposed model improves both the semantic alignment and aesthetic appeal of two diffusion-based T2I models, evidenced by multiple benchmarks (+1.7% on TIFA, +2.9% on DSG1K, +3.4% on VILA aesthetic).
Found in the middle: Calibrating Positional Attention Bias Improves Long Context Utilization (2024.findings-acl)

Copied to clipboard

Challenge: Large language models struggle to capture relevant information located in the middle of their input.
Approach: They propose a calibration mechanism that allows the model to attend to contexts faithfully according to their relevance even when they are in the middle.
Outcome: The proposed calibration mechanism mitigates this positional bias and improves retrieval-augmented generation performance.
Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes (2023.findings-acl)

Copied to clipboard

Challenge: Deploying large language models (LLMs) is difficult because they are memory inefficient and compute-intensive for practical applications.
Approach: They propose a mechanism that fine tunes or distills small models that outperform LLMs . they use human labels to fine tune models or LLM-generated labels to train models .
Outcome: The proposed method outperforms LLMs by using fewer training examples compared to few-shot prompted models using substantially smaller model sizes.
Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering (2021.acl-long)

Copied to clipboard

Challenge: Currently, language-equipped vision systems such as VizWiz, TapTapSee, BeMyEyes, and CamFind are actively being deployed across a broad spectrum of users.
Approach: They propose to identify collective outliers in active learning methods that are hard and often impossible for models to learn . they also propose to use visual inputs to identify these outlier examples as examples assigned low model confidence and prediction variability during training.
Outcome: The proposed methods outperform random selection on visual question answering tasks.
Is C4 Dataset Optimal for Pruning? An Investigation of Calibration Data for LLM Pruning (2024.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to prune LLMs rely on the C4 dataset as calibration data . arithmetic datasets perform better than pre-training datasets for pruning, whereas chain-of-thought is only useful on certain tasks.
Approach: They evaluate the selection of calibration data for LLM pruning across a wide range of datasets . they find that C4 is not the optimal calibration data, and that CoT is only useful on certain tasks.
Outcome: The chosen calibration data significantly impacts the performance of pruned LLMs, the authors found . their results shed light on the importance of carefully selecting calibration data for LLM pruning .
LATTE: Learning to Think with Vision Specialists (2025.emnlp-main)

Copied to clipboard

Challenge: Open-source vision-language models excel on simple question-answering tasks, but struggle with complex questions that require both perception and reasoning.
Approach: They propose a family of vision-language models that have LeArned to Think wiTh vision spEcialists by offloading perception to state-of-the-art vision models.
Outcome: The proposed model achieves 4-5% gains over baselines across 6 benchmarks covering both perception and reasoning abilities.
Wait, We Don’t Need to “Wait”! Removing Thinking Tokens Improves Reasoning Efficiency (2025.findings-emnlp)

Copied to clipboard

Challenge: Recent advances in large reasoning models often introduce significant overthinking . this leads to verbose and redundant outputs that hinder efficiency.
Approach: They propose a plug-and-play solution that disables explicit self-reflection . it suppresses tokens such as "Wait" and "Hmm" during inference .
Outcome: The proposed approach reduces chain-of-thought trajectory length by up to 27%–51% in five R1-style model series without compromising model utility.
ImageInWords: Unlocking Hyper-Detailed Image Descriptions (2024.emnlp-main)

Copied to clipboard

Challenge: generating accurate hyper-detailed image descriptions is challenging for vision-language models trained on web-scraped image-text.
Approach: They propose a data-centric framework for generating hyper-detailed image descriptions using web-scraped image-text.
Outcome: The proposed framework improves on human evaluations on the data, even with only 9k samples.
Scaling Text-Rich Image Understanding via Code-Guided Synthetic Multimodal Data Generation (2025.acl-long)

Copied to clipboard

Challenge: Vision-language models struggle to understand text-rich images due to the scarcity of diverse text-only large language data.
Approach: They propose a framework that leverages the coding capabilities of text-only large language models to create synthetic text-rich multimodal data.
Outcome: The proposed framework can generate high-quality instruction-tuning data using Python, HTML, LaTeX and other languages.
Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps (2024.emnlp-main)

Copied to clipboard

Challenge: Despite the utility and impressive capabilities of large language models, their tendency to generate hallucinations presents a significant challenge in their deployment.
Approach: They propose a simple hallucination detection model based on the ratio of attention weights on the context versus newly generated tokens.
Outcome: The proposed model reduces the amount of hallucinations by 9.6% in a summarization task.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations