66 citations · 107 across the 39 of their papers we have counts for
31 papers · 1 filter
Selection Is Not Learning: Choosing Model Futures
Haoyi Yang, Kshitij Mishra, Nils Lukas +1
Self-evolving language models train on tasks they generate, so every round must decide which updated model the next round inherits. Current loops such as R-Zero, Agent0, and Skill…
TRACER: Trace-Regularized Training Against Indirect Prompt Injection
Kshitij Mishra, Salem Lahlou, Nils Lukas
Indirect prompt injection uses untrusted retrieved content, tool outputs, or agent messages to override an LLM's intended behavior. We show that defense robustness is channel-condi…
Learning a Mixture of GFlowNets
Tiago da Silva, Amauri H. Souza, Salem Lahlou
Learning an ensemble of GFlowNets to sample from a discrete target distribution has become a common approach for achieving better state space exploration and convergence than that…
Particle GFlowNets: Rethinking Generative Marginalization Models
Tiago da Silva, Diego Mesquita, Salem Lahlou
Generative Marginalization Models (MaMs) have been recently introduced as efficient neural sampling models for any-order autoregressive modelling of discrete distributions. By lear…
CopyShield: A Cross-Level Benchmark of Copyright Defenses in LLMs
Maryam Alshehyari, Dushyant Singh Chauhan, Samuele Poppi +3
Large language models can reproduce memorized text verbatim, yet copyright defenses are usually evaluated under incompatible protocols. We introduce CopyShield, a controlled benchm…
Path-dependent Discrete Amortized Inference
Tiago da Silva, Esmeralda S. Whitammer, Salem Lahlou
We consider the problem of sampling compositional and discrete objects from a given unnormalized posterior distribution. Notably, recent studies have shown that this problem can be…
Entropy-Gated Latent Recursion
Soham Bhattacharjee, Dushyant Singh Chauhan, Salem Lahlou +2
Inference-time scaling has become the dominant lever for improving language-model reasoning, but existing methods derive rollout diversity from a single source: stochastic token-le…
Byzantine Cheap Talk: Adversarial Resilience and Topology Effects in LLM Coordination Games
Aya El Mir, Martin Takáč, Salem Lahlou
Multi-agent LLM systems increasingly rely on communication protocols for coordination, yet their robustness under adversarial and structural constraints remains poorly understood.…
Bayesian Rain Field Reconstruction using Commercial Microwave Links and Diffusion Model Priors
Badr Moufad, Albina Ilina, Hai Victor Habi +4
Commercial Microwave Links (CMLs) offer dense spatial coverage for rainfall sensing but produce path-integrated measurements that make accurate ground-level reconstruction challeng…
Avoid What You Know: Divergent Trajectory Balance for GFlowNets
Pedro Dall'Antonia, Tiago da Silva, Daniel Csillag +2
Generative Flow Networks (GFlowNets) are a flexible family of amortized samplers trained to generate discrete and compositional objects with probability proportional to a reward fu…
Zero-Shot Off-Policy Learning
Arip Asadulaev, Maksim Bobrin, Salem Lahlou +3
Off-policy learning methods seek to derive an optimal policy directly from a fixed dataset of prior interactions. This objective presents significant challenges, primarily due to t…
Curriculum-Augmented GFlowNets For mRNA Sequence Generation
Aya Laajil, Abduragim Shtanchaev, Sajan Muhammad +4
We develop an approach for the de novo synthesis of messenger RNA (mRNA) sequences encoding target proteins. This requires optimizing multiple biological objectives over large comb…
Noise-corrected GRPO: From Noisy Rewards to Unbiased Gradients
Omar El Mansouri, Fathinah Asma Izzati, Mohamed El Amine Seddik +1
Reinforcement learning from human feedback (RLHF) or verifiable rewards (RLVR), the standard paradigm for aligning LLMs or building recent SOTA reasoning models, is highly sensitiv…
Communication Enables Cooperation in LLM Agents: A Comparison with Curriculum-Based Approaches
Hachem Madmoun, Salem Lahlou
Eliciting cooperation in multi-agent LLM systems is critical for AI alignment. We investigate two approaches: direct communication and curriculum learning. In a 4-player Stag Hunt,…
Improved Exploration in GFlownets via Enhanced Epistemic Neural Networks
Sajan Muhammad, Salem Lahlou
Efficiently identifying the right trajectories for training remains an open problem in GFlowNets. To address this, it is essential to prioritize exploration in regions of the state…
Semantic Communication meets System 2 ML: How Abstraction, Compositionality and Emergent Languages Shape Intelligence
Mehdi Bennis, Salem Lahlou
The trajectories of 6G and AI are set for a creative collision. However, current visions for 6G remain largely incremental evolutions of 5G, while progress in AI is hampered by bri…
Loss-Guided Auxiliary Agents for Overcoming Mode Collapse in GFlowNets
Idriss Malek, Aya Laajil, Abhijith Sharma +2
Although Generative Flow Networks (GFlowNets) are designed to capture multiple modes of a reward function, they often suffer from mode collapse in practice, getting trapped in earl…
Accurate and Diverse LLM Mathematical Reasoning via Automated PRM-Guided GFlowNets
Adam Younsi, Ahmed Attia, Abdalgader Abubaker +3
Achieving both accuracy and diverse reasoning remains challenging for Large Language Models (LLMs) in complex domains like mathematics. A key bottleneck is evaluating intermediate…
On the Privacy Risks of Spiking Neural Networks: A Membership Inference Analysis
Junyi Guan, Abhijith Sharma, Chong Tian +1
Spiking Neural Networks (SNNs) are increasingly explored for their energy efficiency and robustness in real-world applications, yet their privacy risks remain largely unexamined. I…
On Generalization for Generative Flow Networks
Anas Krichel, Nikolay Malkin, Salem Lahlou +1
Generative Flow Networks (GFlowNets) have emerged as an innovative learning paradigm designed to address the challenge of sampling from an unnormalized probability distribution, ca…
PORT: Preference Optimization on Reasoning Traces
Salem Lahlou, Abdalgader Abubaker, Hakim Hacid
Preference optimization methods have been successfully applied to improve not only the alignment of large language models (LLMs) with human values, but also specific natural langua…
Investigating Regularization of Self-Play Language Models
Reda Alami, Abdalgader Abubaker, Mastane Achab +2
This paper explores the effects of various forms of regularization in the context of language model alignment via self-play. While both reinforcement learning from human feedback (…
BatchGFN: Generative Flow Networks for Batch Active Learning
Shreshth A. Malik, Salem Lahlou, Andrew Jesson +5
We introduce BatchGFN -- a novel approach for pool-based active learning that uses generative flow networks to sample sets of data points proportional to a batch reward. With an ap…
Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks
Maxime Chevalier-Boisvert, Bolun Dai, Mark Towers +6
We present the Minigrid and Miniworld libraries which provide a suite of goal-oriented 2D and 3D environments. The libraries were explicitly created with a minimalistic design para…