66 citations · 107 across the 39 of their papers we have counts for
46 papers
PROBE: Learning to Audit Policy Compliance in Tool-Using LLM Agents
Kshitij Mishra, Abhijith Sharma, Nils Lukas +1
Modern agentic systems extend language models with external tools, enabling them to complete complex tasks through multi-turn interactions. As these agents are deployed in conseque…
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…
Score-Only Distillation for Compact Dense Retrieval
Kirill Dubovikov, Martin Takac, Salem Lahlou
Large embedding models improve retrieval quality, but serving large encoders online is expensive. We study whether a compact retriever can learn teacher ranking behavior from score…
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…
Position: agentic AI orchestration should be Bayes-consistent
Theodore Papamarkou, Pierre Alquier, Matthias Bauer +27
LLMs excel at predictive tasks and complex reasoning tasks, but many high-value deployments rely on decisions under uncertainty, for example, which tool to call, which expert to co…
SAHM: A Benchmark for Arabic Financial and Shari'ah-Compliant Reasoning
Rania Elbadry, Sarfraz Ahmad, Ahmed Heakl +12
English financial NLP has advanced rapidly through benchmarks targeting earnings analysis, market sentiment, tabular reasoning, and financial question answering, yet Arabic financi…
Temporal Contrastive Decoding: A Training-Free Method for Large Audio-Language Models
Yanda Li, Yuhan Liu, Zirui Song +3
Large audio-language models (LALMs) generalize across speech, sound, and music, but unified decoders can exhibit a \emph{temporal smoothing bias}: transient acoustic cues may be un…
Breaking the Martingale Curse: Multi-Agent Debate via Asymmetric Cognitive Potential Energy
Yuhan Liu, Juntian Zhang, Yichen Wu +4
Multi-Agent Debate (MAD) has emerged as a promising paradigm for enhancing large language model reasoning. However, recent work reveals a limitation:standard MAD cannot improve bel…
HyperKKL: Enabling Non-Autonomous State Estimation through Dynamic Weight Conditioning
Yahia Salaheldin Shaaban, Salem Lahlou, Abdelrahman Sayed Sayed
This paper proposes HyperKKL, a novel learning approach for designing Kazantzis-Kravaris/Luenberger (KKL) observers for non-autonomous nonlinear systems. While KKL observers offer…
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…
ArabicDialectHub: A Cross-Dialectal Arabic Learning Resource and Platform
Salem Lahlou
We present ArabicDialectHub, a cross-dialectal Arabic learning resource comprising 552 phrases across six varieties (Moroccan Darija, Lebanese, Syrian, Emirati, Saudi, and MSA) and…
SD-E: Semantic Exploration for Reasoning Under Token Budgets
Kshitij Mishra, Nils Lukas, Salem Lahlou
Small language models (SLMs) struggle with complex reasoning because exploration is expensive under tight compute budgets. We introduce Semantic Diversity-Exploration-Exploitation…
CORE: Collaborative Reasoning via Cross Teaching
Kshitij Mishra, Mirat Aubakirov, Martin Takac +2
Large language models exhibit complementary reasoning errors: on the same instance, one model may succeed with a particular decomposition while another fails. We propose Collaborat…
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,…