3 citations · 4 across the 22 of their papers we have counts for
23 papers
LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL
Yujin Kim, Namgyu Ho, Sangmin Hwang +7
Reinforcement learning (RL) for non-verifiable instruction following increasingly relies on LLM judges with prompt-specific rubrics as reward signals. While recent methods adapt th…
Cosmos 3: Omnimodal World Models for Physical AI
NVIDIA, :, Aditi +293
We introduce Cosmos 3, a family of omnimodal world models designed to jointly process and generate language, image, video, audio, and action sequences within a unified mixture-of-t…
ProCUA-SFT Technical Report
Jaehun Jung, Ximing Lu, Brandon Cui +11
Training computer-use agents (CUAs) -- models that interact with graphical desktops through screenshots and keyboard/mouse actions -- requires large-scale, diverse trajectory data…
Introspective X Training: Feedback Conditioning Improves Scaling Across all LLM Training Stages
Brandon Cui, Ximing Lu, Jaehun Jung +7
We tackle the question of how to scale more efficiently across the many, ever-growing stages of current LLM training pipelines. Our guiding intuition stems from the fact that the d…
How to Instruct Your Robot: Dense Language Annotations Power Robot Policy Learning
Bosung Kim, Ruiyi Wang, David Acuna +5
Scaling robot policy learning is bottlenecked by the cost of collecting demonstrations, while language annotations for existing demonstrations are comparatively cheap. We study lan…
Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence
NVIDIA, :, Amala Sanjay Deshmukh +204
We introduce Nemotron 3 Nano Omni, the latest model in the Nemotron multimodal series and the first to natively support audio inputs alongside text, images, and video. Nemotron 3 N…
DeltaPrompts: Escaping the Zero-Delta Trap in Multimodal Distillation
Jaehun Jung, Hyunwoo Kim, Brandon Cui +4
Distillation enables compact Vision-Language Models (VLMs) to obtain strong reasoning capabilities, yet the prompts driving this process are typically chosen via simple heuristics…
Synthetic Mixed Training: Scaling Parametric Knowledge Acquisition Beyond RAG
Seungju Han, Konwoo Kim, Chanwoo Park +5
Synthetic data augmentation helps language models learn new knowledge in data-constrained domains. However, naively scaling existing synthetic data methods by training on more synt…
Privasis: Synthesizing the Largest "Public" Private Dataset from Scratch
Hyunwoo Kim, Niloofar Mireshghallah, Michael Duan +11
Research involving privacy-sensitive data has always been constrained by data scarcity, standing in sharp contrast to other areas that have benefited from data scaling. This challe…
Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text
Ximing Lu, David Acuna, Jaehun Jung +12
Reinforcement Learning with Verifiable Rewards (RLVR) has become a cornerstone for unlocking complex reasoning in Large Language Models (LLMs). Yet, scaling up RL is bottlenecked b…
Long Grounded Thoughts: Synthesizing Visual Problems and Reasoning Chains at Scale
David Acuna, Chao-Han Huck Yang, Yuntian Deng +6
Despite rapid progress, multimodal reasoning still lacks a systematic approach to synthesize large-scale vision-centric datasets beyond visual math. We introduce a framework able t…
ProfBench: Multi-Domain Rubrics requiring Professional Knowledge to Answer and Judge
Zhilin Wang, Jaehun Jung, Ximing Lu +7
Evaluating progress in large language models (LLMs) is often constrained by the challenge of verifying responses, limiting assessments to tasks like mathematics, programming, and s…
NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model
NVIDIA, :, Aarti Basant +214
We introduce Nemotron-Nano-9B-v2, a hybrid Mamba-Transformer language model designed to increase throughput for reasoning workloads while achieving state-of-the-art accuracy compar…
The Surprising Effectiveness of Membership Inference with Simple N-Gram Coverage
Skyler Hallinan, Jaehun Jung, Melanie Sclar +7
Membership inference attacks serves as useful tool for fair use of language models, such as detecting potential copyright infringement and auditing data leakage. However, many curr…
The Curious Case of Factuality Finetuning: Models' Internal Beliefs Can Improve Factuality
Benjamin Newman, Abhilasha Ravichander, Jaehun Jung +5
Language models are prone to hallucination - generating text that is factually incorrect. Finetuning models on high-quality factual information can potentially reduce hallucination…
Socratic-MCTS: Test-Time Visual Reasoning by Asking the Right Questions
David Acuna, Ximing Lu, Jaehun Jung +4
Recent research in vision-language models (VLMs) has centered around the possibility of equipping them with implicit long-form chain-of-thought reasoning -- akin to the success obs…
Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers
Wooseok Seo, Seungju Han, Jaehun Jung +6
Fact verification is essential for ensuring the reliability of LLM applications. In this study, we evaluate 12 pre-trained LLMs and one specialized fact-verifier, including frontie…
Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning
Jaehun Jung, Seungju Han, Ximing Lu +7
Effective generalization in language models depends critically on the diversity of their training data. Yet existing diversity metrics often fall short of this goal, relying on sur…
Retro-Search: Exploring Untaken Paths for Deeper and Efficient Reasoning
Ximing Lu, Seungju Han, David Acuna +8
Large reasoning models exhibit remarkable reasoning capabilities via long, elaborate reasoning trajectories. Supervised fine-tuning on such reasoning traces, also known as distilla…
Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement
Jaehun Jung, Faeze Brahman, Yejin Choi
We present a principled approach to provide LLM-based evaluation with a rigorous guarantee of human agreement. We first propose that a reliable evaluation method should not uncriti…
Information-Theoretic Distillation for Reference-less Summarization
Jaehun Jung, Ximing Lu, Liwei Jiang +4
The current winning recipe for automatic summarization is using proprietary large-scale language models (LLMs) such as ChatGPT as is, or imitation learning from them as teacher mod…
JAMDEC: Unsupervised Authorship Obfuscation using Constrained Decoding over Small Language Models
Jillian Fisher, Ximing Lu, Jaehun Jung +3
The permanence of online content combined with the enhanced authorship identification techniques calls for stronger computational methods to protect the identity and privacy of onl…
STEER: Unified Style Transfer with Expert Reinforcement
Skyler Hallinan, Faeze Brahman, Ximing Lu +3
While text style transfer has many applications across natural language processing, the core premise of transferring from a single source style is unrealistic in a real-world setti…