Salem Lahlou

Assistant Professor of Machine Learning

Home Publications Talks Teaching Group Community CV Scholar
Publications | Salem Lahlou

Publications

Full author lists are in the CV and on Google Scholar.

Journal & Conference Papers

2026

  • FinChain: A Symbolic Benchmark for Verifiable Chain-of-Thought Financial Reasoning. ACL 2026
  • SAHM: Arabic Financial Instruction-Tuning Dataset and Models. ACL 2026
  • Temporal Contrastive Decoding: A Training-Free Method for Large Audio-Language Models. Findings of ACL 2026
  • Byzantine Cheap Talk: Adversarial Resilience and Topology Effects in LLM Coordination Games. NETYS 2026
  • Communication Enables Cooperation in LLM Agents: A Comparison with Curriculum-Based Approaches. EACL 2026 (Oral)
  • SD-E2: Semantic Exploration for Reasoning Under Token Budgets. Findings of EACL 2026
  • TorchGFN: A PyTorch GFlowNet Library. JMLR 2026 (+ NeurIPS 2025 Workshop on Frontiers in Probabilistic Inference)

2025

  • Loss-guided Auxiliary Agents for Overcoming Mode Collapse in GFlowNets. AAAI 2026
  • Improved Exploration in GFlowNets via Enhanced Epistemic Neural Networks. ICoIAS 2025
  • Assessing the Capabilities of Large Language Models for Oil and Gas Industry Applications. ADIPEC 2025
  • PORT: Preference Optimization on Reasoning Traces. NAACL 2025
  • On the Privacy Risks of Spiking Neural Networks: A Membership Inference Analysis. UAI 2025 (+ oral at ICLR 2025 Workshop ICBINB)
  • SVRPBench: A Realistic Benchmark for Stochastic Vehicle Routing Problem. NeurIPS 2025

2023

  • GFlowOut: Dropout with Generative Flow Networks. ICML 2023
  • A Theory of Continuous Generative Flow Networks. ICML 2023
  • GFlowNet Foundations. JMLR 2023
  • GFlowNets and Variational Inference. ICLR 2023
  • DEUP: Direct Epistemic Uncertainty Prediction. TMLR 2023
  • MiniGrid & MiniWorld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks. NeurIPS 2023

2019

  • BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning. ICLR 2019

2017

  • A Nash Equilibrium Formulation of a Tradable Credits Scheme for Incentivizing Transport Choices. Transportation Research Part B 2017

Workshop Papers & Extended Abstracts

2026

  • HyperKKL: Enabling Non-Autonomous State Estimation through Dynamic Weight Conditioning. AI&PDE Workshop at ICLR 2026
  • Avoid What You Know: Divergent Trajectory Balance for GFlowNets. ICLR 2026 DeLTa Workshop (accepted); under review at ICML 2026

2025

  • Curriculum-Augmented GFlowNets for mRNA Sequence Generation. NeurIPS 2025 Machine Learning in Structural Biology Workshop; under review at UAI 2026
  • Mitigating Societal Cognitive Overload in the Age of AI: Challenges and Directions. ICLR 2025 Workshop on Bidirectional Human-AI Alignment (to appear in PMLR)
  • Customer Reactions to Companion AI: Exploring Opportunities and Threats for Vulnerable Consumers. Frontiers in Service 2025

2023

  • BatchGFlowNet: Generative Flow Networks for Batch Active Learning. ICML 2023 SPIGM Workshop

Preprints & Under Review

2026

  • PERSUADE: A Debate Arena for Benchmarking, Optimizing, and Auditing Persuasion in Language Models. Under review at COLM 2026
  • Accurate and Diverse LLM Mathematical Reasoning via Automated PRM-Guided GFlowNets. Under review at COLM 2026
  • Noise-Corrected GRPO: From Noisy Rewards to Unbiased Gradients. Under review at ICML 2026
  • Zero-Shot Off-Policy Learning. Under review at ICML 2026
  • Breaking the Martingale Curse: Multi-Agent Debate via Asymmetric Cognitive Potential Energy. Under review at ICML 2026
  • Bayesian Rain Field Reconstruction using Commercial Microwave Links and Diffusion Model Priors. Under review at ICML 2026
  • Path-dependent Discrete Amortized Inference. Under review at ICML 2026
  • Particle GFlowNets: Rethinking Generative Marginalization Models. Under review at UAI 2026
  • CoRe: Collaborative Reasoning via Cross Teaching. Under review at ICML 2026
  • Position: Agentic AI Systems Should Be Making Bayes-Consistent Decisions. Under review at ICML 2026 (Position Paper Track)
  • Bayesian Experimental Design: Bridging Optimization and Causal Discovery. Under review at IJCAI-ECAI 2026 Survey Track
  • Expert-Aided Causal Discovery of Ancestral Graphs. Under review at Information Sciences

2025

  • LLM-BABYBENCH: Understanding and Evaluating Grounded Planning and Reasoning in LLMs. arXiv:2505.12135
  • Semantic Communication Meets System 2 ML: How Abstraction, Compositionality and Emergent Languages Shape Intelligence. arXiv:2505.20964

2024

  • On Generalization for Generative Flow Networks. arXiv:2407.03105
  • Investigating Regularization of Self-Play Language Models. arXiv:2404.04291

2020

  • Mastering Rate-Based Curriculum Learning. arXiv preprint arXiv:2008.06456

Thesis and Edited Volumes