71 citations · 128 across the 18 of their papers we have counts for
23 papers
Rationale-Guided Policy Optimization: Learning to Reason with Adaptive Rationale Scaffolding
Hoang Phan, Minh Pham, Chau Pham +3
On-policy reinforcement learning has become a central paradigm for improving the reasoning abilities of large language models. However, its effectiveness is often limited by reward…
Break Me If You Can: Self-Jailbreaking of Aligned LLMs via Lexical Insertion Prompting
Devang Kulshreshtha, Hang Su, Haibo Jin +2
We introduce \emph{self-jailbreaking}, a threat model in which an aligned LLM guides its own compromise. Unlike most jailbreak techniques, which often rely on handcrafted prompts o…
Query Efficient Structured Matrix Learning
Noah Amsel, Pratyush Avi, Tyler Chen +5
We study the problem of learning a structured approximation (low-rank, sparse, banded, etc.) to an unknown matrix given access to matrix-vector product (matvec) queries of the…
MARVIS: Modality Adaptive Reasoning over VISualizations
Benjamin Feuer, Lennart Purucker, Oussama Elachqar +1
Predictive applications of machine learning often rely on small (sub 1 Bn parameter) specialized models tuned to particular domains or modalities. Such models often achieve excelle…
OpenThoughts: Data Recipes for Reasoning Models
Etash Guha, Ryan Marten, Sedrick Keh +47
Reasoning models have made rapid progress on many benchmarks involving math, code, and science. Yet, there are still many open questions about the best training recipes for reasoni…
VeriThoughts: Enabling Automated Verilog Code Generation using Reasoning and Formal Verification
Patrick Yubeaton, Andre Nakkab, Weihua Xiao +4
This paper introduces VeriThoughts, a novel dataset designed for reasoning-based Verilog code generation. We establish a new benchmark framework grounded in formal verification met…
When Are Concepts Erased From Diffusion Models?
Kevin Lu, Nicky Kriplani, Rohit Gandikota +4
In concept erasure, a model is modified to selectively prevent it from generating a target concept. Despite the rapid development of new methods, it remains unclear how thoroughly…
SEAL: Semantic Aware Image Watermarking
Kasra Arabi, R. Teal Witter, Chinmay Hegde +1
Generative models have rapidly evolved to generate realistic outputs. However, their synthetic outputs increasingly challenge the clear distinction between natural and AI-generated…
SolidMark: Evaluating Image Memorization in Generative Models
Nicky Kriplani, Minh Pham, Gowthami Somepalli +2
Recent works have shown that diffusion models are able to memorize training images and emit them at generation time. However, the metrics used to evaluate memorization and its miti…
Huff-LLM: End-to-End Lossless Compression for Efficient LLM Inference
Patrick Yubeaton, Tareq Mahmoud, Shehab Naga +8
As they become more capable, large language models (LLMs) have continued to rapidly increase in size. This has exacerbated the difficulty in running state of the art LLMs on small,…
WILDCHAT-50M: A Deep Dive Into the Role of Synthetic Data in Post-Training
Benjamin Feuer, Chinmay Hegde
Language model (LLM) post-training, from DPO to distillation, can refine behaviors and unlock new skills, but the open science supporting these post-training techniques is still in…
TruncFormer: Private LLM Inference Using Only Truncations
Patrick Yubeaton, Jianqiao Cambridge Mo, Karthik Garimella +4
Private inference (PI) serves an important role in guaranteeing the privacy of user data when interfacing with proprietary machine learning models such as LLMs. However, PI remains…
Hidden in the Noise: Two-Stage Robust Watermarking for Images
Kasra Arabi, Benjamin Feuer, R. Teal Witter +2
As the quality of image generators continues to improve, deepfakes become a topic of considerable societal debate. Image watermarking allows responsible model owners to detect and…
SELECT: A Large-Scale Benchmark of Data Curation Strategies for Image Classification
Benjamin Feuer, Jiawei Xu, Niv Cohen +3
Data curation is the problem of how to collect and organize samples into a dataset that supports efficient learning. Despite the centrality of the task, little work has been devote…
Evaluation and Comparison of Visual Language Models for Transportation Engineering Problems
Sanjita Prajapati, Tanu Singh, Chinmay Hegde +1
Recent developments in vision language models (VLM) have shown great potential for diverse applications related to image understanding. In this study, we have explored state-of-the…
LiveBench: A Challenging, Contamination-Limited LLM Benchmark
Colin White, Samuel Dooley, Manley Roberts +15
Test set contamination, wherein test data from a benchmark ends up in a newer model's training set, is a well-documented obstacle for fair LLM evaluation and can quickly render ben…
BioTrove: A Large Curated Image Dataset Enabling AI for Biodiversity
Chih-Hsuan Yang, Benjamin Feuer, Zaki Jubery +12
We introduce BioTrove, the largest publicly accessible dataset designed to advance AI applications in biodiversity. Curated from the iNaturalist platform and vetted to include only…
Agnostic Active Learning of Single Index Models with Linear Sample Complexity
Aarshvi Gajjar, Wai Ming Tai, Xingyu Xu +3
We study active learning methods for single index models of the form , where and ${\mathb…
TuneTables: Context Optimization for Scalable Prior-Data Fitted Networks
Benjamin Feuer, Robin Tibor Schirrmeister, Valeriia Cherepanova +5
While tabular classification has traditionally relied on from-scratch training, a recent breakthrough called prior-data fitted networks (PFNs) challenges this approach. Similar to…
Scaling TabPFN: Sketching and Feature Selection for Tabular Prior-Data Fitted Networks
Benjamin Feuer, Chinmay Hegde, Niv Cohen
Tabular classification has traditionally relied on supervised algorithms, which estimate the parameters of a prediction model using its training data. Recently, Prior-Data Fitted N…
Exploring Dataset-Scale Indicators of Data Quality
Benjamin Feuer, Chinmay Hegde
Modern computer vision foundation models are trained on massive amounts of data, incurring large economic and environmental costs. Recent research has suggested that improving data…
ArcheType: A Novel Framework for Open-Source Column Type Annotation using Large Language Models
Benjamin Feuer, Yurong Liu, Chinmay Hegde +1
Existing deep-learning approaches to semantic column type annotation (CTA) have important shortcomings: they rely on semantic types which are fixed at training time; require a larg…
When Do Neural Nets Outperform Boosted Trees on Tabular Data?
Duncan McElfresh, Sujay Khandagale, Jonathan Valverde +6
Tabular data is one of the most commonly used types of data in machine learning. Despite recent advances in neural nets (NNs) for tabular data, there is still an active discussion…