66 citations · 107 across the 39 of their papers we have counts for
12 papers · 1 filter
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…
FinChain: A Symbolic Benchmark for Verifiable Chain-of-Thought Financial Reasoning
Zhuohan Xie, Daniil Orel, Rushil Thareja +22
Multi-step symbolic reasoning is essential for robust financial analysis; yet, current benchmarks largely overlook this capability. Existing datasets such as FinQA and ConvFinQA em…
SVRPBench: A Realistic Benchmark for Stochastic Vehicle Routing Problem
Ahmed Heakl, Yahia Salaheldin Shaaban, Martin Takac +2
Robust routing under uncertainty is central to real-world logistics, yet most benchmarks assume static, idealized settings. We present SVRPBench, the first open benchmark to captur…
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…
LLM-BabyBench: Can Language Models Plan in Worlds They Can Simulate?
Omar Choukrani, Idriss Malek, Daniil Orel +5
Interactive benchmarks for LLMs usually report a single metric, even though succeeding in them requires models to show several different skills. While those benchmarks are useful f…
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…
Mitigating Societal Cognitive Overload in the Age of AI: Challenges and Directions
Salem Lahlou
Societal cognitive overload, driven by the deluge of information and complexity in the AI age, poses a critical challenge to human well-being and societal resilience. This paper ar…
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…