109 citations · 504 across the 55 of their papers we have counts for
59 papers
Frontier Learning: Training LLM Reasoners at the Edge of Capability
Robin Faro, Shyam Sundhar Ramesh, Ilija Bogunovic +1
Reinforcement Learning-based post-training of Large Language Models (LLM) has been successfully applied to improve their reasoning capabilities. Existing pipelines primarily finetu…
Temporal Self-Distillation: Faster Inference in Discrete Diffusion Language Models
Shijian Xu, Andrea Miele, Metod Jazbec +3
Diffusion language models (dLLMs) promise fast inference by generating multiple tokens in parallel, but suffer severe performance degradation when parallel decoding is pushed too a…
Meta-Learning Preferences for Multilingual LLM Alignment
Jiaying Lin, Seongho Son, Nam Phuong Tran +3
Unequal availability of human preference data across languages poses a significant challenge for aligning large language models in multilingual settings. To address the lack of suf…
SWE-Router: Routing in Multi-turn Agentic Software Engineering Tasks
Seongho Son, Sangwoong Yoon, Jiahua Tang +3
Large language models (LLMs) embedded in multi-turn agentic harnesses are reshaping software engineering (SWE), but routing every task to a frontier model is wasteful when many iss…
Re-evaluating Confidence Remasking in Masked Diffusion Language Models
Stipe Frkovic, Metod Jazbec, Dan Zhang +3
Masked diffusion language models (dLLMs) have recently emerged as a competitive alternative to autoregressive language models, with the promise of faster inference via parallel tok…
PROWL: Prioritized Regret-Driven Optimization for World Model Learning
Ahmet H. Güzel, Jenny Seidenschwarz, Benjamin Graham +3
Modern action-conditioned video world models achieve strong short-horizon visual realism, yet remain unreliable on rare, interaction-critical transitions that dominate downstream p…
GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models
Xiaohang Tang, Keyue Jiang, Che Liu +4
Reinforcement learning (RL) can be used to improve the policy (denoiser) of diffusion large language models (dLLMs), while being hindered by the intractability of the policy likeli…
Overton Pluralistic Reinforcement Learning for Large Language Models
Yu Fu, Seongho Son, Ilija Bogunovic
Existing alignment paradigms remain limited in capturing the pluralistic nature of human values. Overton Pluralism (OP) addresses this gap by generating responses with diverse pers…
LLM-WikiRace Benchmark: How Far Can LLMs Plan over Real-World Knowledge Graphs?
Juliusz Ziomek, William Bankes, Lorenz Wolf +3
We introduce LLM-Wikirace, a benchmark for evaluating planning, reasoning, and world knowledge in large language models (LLMs). In LLM-Wikirace, models must efficiently navigate Wi…
Multi-Task GRPO: Reliable LLM Reasoning Across Tasks
Shyam Sundhar Ramesh, Xiaotong Ji, Matthieu Zimmer +5
RL-based post-training with GRPO is widely used to improve large language models on individual reasoning tasks. However, real-world deployment requires reliable performance across…
Robust Bayesian Optimisation with Unbounded Corruptions
Abdelhamid Ezzerg, Ilija Bogunovic, Jeremias Knoblauch
Bayesian Optimization is critically vulnerable to extreme outliers. Existing provably robust methods typically assume a bounded cumulative corruption budget, which makes them defen…
Imagined Autocurricula
Ahmet H. Güzel, Matthew Thomas Jackson, Jarek Luca Liesen +4
Training agents to act in embodied environments typically requires vast training data or access to accurate simulation, neither of which exists for many cases in the real world. In…
Synthetic Data is Sufficient for Zero-Shot Visual Generalization from Offline Data
Ahmet H. Güzel, Ilija Bogunovic, Jack Parker-Holder
Offline reinforcement learning (RL) offers a promising framework for training agents using pre-collected datasets without the need for further environment interaction. However, pol…
wd1: Weighted Policy Optimization for Reasoning in Diffusion Language Models
Xiaohang Tang, Rares Dolga, Sangwoong Yoon +1
Improving the reasoning capabilities of diffusion-based large language models (dLLMs) through reinforcement learning (RL) remains an open problem. The intractability of dLLMs likel…
This Is Your Doge, If It Please You: Exploring Deception and Robustness in Mixture of LLMs
Lorenz Wolf, Sangwoong Yoon, Ilija Bogunovic
Mixture of large language model (LLMs) Agents (MoA) architectures achieve state-of-the-art performance on prominent benchmarks like AlpacaEval 2.0 by leveraging the collaboration o…
Robust Multi-Objective Controlled Decoding of Large Language Models
Seongho Son, William Bankes, Sangwoong Yoon +3
We introduce Robust Multi-Objective Decoding (RMOD), a novel inference-time algorithm that robustly aligns Large Language Models (LLMs) to multiple human objectives (e.g., instruct…
RSPO: Regularized Self-Play Alignment of Large Language Models
Xiaohang Tang, Sangwoong Yoon, Seongho Son +3
Self-play-based policy optimization has emerged as an effective approach for fine-tuning large language models (LLMs), formulating preference optimization as a two-player game. How…
Mean-Field Bayesian Optimisation
Petar Steinberg, Juliusz Ziomek, Matej Jusup +1
We address the problem of optimising the average payoff for a large number of cooperating agents, where the payoff function is unknown and treated as a black box. While standard Ba…
On Almost Surely Safe Alignment of Large Language Models at Inference-Time
Xiaotong Ji, Shyam Sundhar Ramesh, Matthieu Zimmer +3
We introduce a novel inference-time alignment approach for LLMs that aims to generate safe responses almost surely, i.e., with probability approaching one. Our approach models the…
No-Regret Linear Bandits under Gap-Adjusted Misspecification
Chong Liu, Dan Qiao, Ming Yin +2
This work studies linear bandits under a new notion of gap-adjusted misspecification and is an extension of Liu et al. (2023). When the underlying reward function is not linear, ex…
Sample-Efficient Regret-Minimizing Double Oracle in Extensive-Form Games
Xiaohang Tang, Chiyuan Wang, Chengdong Ma +3
Extensive-Form Game (EFG) represents a fundamental model for analyzing sequential interactions among multiple agents and the primary challenge to solve it lies in mitigating sample…
Sample-efficient Bayesian Optimisation Using Known Invariances
Theodore Brown, Alexandru Cioba, Ilija Bogunovic
Bayesian optimisation (BO) is a powerful framework for global optimisation of costly functions, using predictions from Gaussian process models (GPs). In this work, we apply BO to f…
Right Now, Wrong Then: Non-Stationary Direct Preference Optimization under Preference Drift
Seongho Son, William Bankes, Sayak Ray Chowdhury +2
Current Large Language Model (LLM) preference optimization algorithms do not account for temporal preference drift, which can lead to severe misalignment. To address this limitatio…
Adversarially Robust Decision Transformer
Xiaohang Tang, Afonso Marques, Parameswaran Kamalaruban +1
Decision Transformer (DT), as one of the representative Reinforcement Learning via Supervised Learning (RvS) methods, has achieved strong performance in offline learning tasks by l…