activity
20242026
collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG2026

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…

cs.LG2025

When Judgment Becomes Noise: How Design Failures in LLM Judge Benchmarks Silently Undermine Validity

Benjamin Feuer, Chiung-Yi Tseng, Astitwa Sarthak Lathe +2

LLM-judged benchmarks are increasingly used to evaluate complex model behaviors, yet their design introduces failure modes absent in conventional ground-truth based benchmarks. We…

cs.LG2025

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…

cs.LG2025

Towards Large Reasoning Models for Agriculture

Hossein Zaremehrjerdi, Shreyan Ganguly, Ashlyn Rairdin +17

Agricultural decision-making involves complex, context-specific reasoning, where choices about crops, practices, and interventions depend heavily on geographic, climatic, and econo…

cs.LG2025

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…

cs.LG2025

Style Outweighs Substance: Failure Modes of LLM Judges in Alignment Benchmarking

Benjamin Feuer, Micah Goldblum, Teresa Datta +5

The release of ChatGPT in November 2022 sparked an explosion of interest in post-training and an avalanche of new preference optimization (PO) methods. These methods claim superior…