Publications

Special issue dedicated to the International Symposium on Mathematical Programming (ISMP), Montréal, 2024
Youssef Diouane
Franklin Djeumou Fomeni
Alain Hertz
Dominique Orban
Sandscapes: self-modifying energy landscapes with emergent branching and flips
Nacer Eddine Boukacem
Madhav Mani
Energy landscapes provide a common framework for describing learning, embryonic development, and collective dynamics. Although such landscap… (see more)es may evolve over time, their dynamics are typically prescribed externally rather than generated by the system itself. Here we get inspiration from biology to introduce sandscapes : self-modifying landscapes in which the motions of interacting agents continuously reshape the landscape that governs their own trajectories. We derive sandscapes from a minimal model of interacting Hopfield units, where the basins of each attractor are modulated by their occupancies. Sandscapes spontaneously generate sequential symmetry breaking and differentiation trees, with local branching described by coupled Ising dynamics. We then drive the dynamics of sandscapes (using local proliferation common in biology) and leverage catastrophe theory to show that sandscapes self-organize toward flip bifurcations, suggesting a generic mechanism for the emergence of ubiquitous binary cell-fate decisions. We further demonstrate that sandscapes can act as generative models of developmental trajectories : starting from terminal states alone, we reconstruct realistic hematopoietic differentiation trees with multiple layers of intermediate progenitor states. More broadly, our results identify sandscapes as a general principle of adaptive dynamics, explaining how feedback between agents and landscapes produces branching, criticality, and self-organization across learning and biology.
World Models as Adversaries: Multi-Agent Self-Play Fine-Tuning for Robust Motion Planning
Tong Nie
Yuewen Mei
Junlin He
Jian Sun
Wei Ma
Robust motion planning in dense traffic requires autonomous vehicles to interact in rare and safety-critical scenarios that are underreprese… (see more)nted in naturalistic driving data. Although adversarial training offers a feasible solution, existing methods often rely on external scenario generators, heuristic perturbations, or simulator-heavy rollouts, which makes them difficult to integrate with modern autoregressive planners. Here, we cast adversarially robust planner learning as a constrained min-max game and propose Adversarial World Modeling (AWM), a theoretically grounded multi-agent self-play fine-tuning framework. Since solving the exact game is intractable, AWM introduces a principled decoupled solver. In the inner minimization, the planner's predictive world model is converted into a role-conditioned adversary that learns sparse, scene-adaptive attack coalitions via counterfactual credit assignment. In the outer maximization, the ego planner optimizes a regret-aware robust best response against the frozen AWM, utilizing tail-risk weighting and reference-anchored trust regions to improve hard-case recovery while preserving nominal driving behavior. Experiments on the nuPlan and InterPlan benchmarks demonstrate that our method generates transferable adversarial interactions and yields a robust planner that achieves competitive closed-loop performance in both nominal and highly interactive long-tail scenarios. Theoretical analysis justifies the decoupled solver and the main optimization components.
Co-evolution of self-replication and function in a digital primordial soup
Francesco Cicala
Eyvind Niklasson
Ettore Randazzo
Sami Boukortt
Alessio Basti
Mayalen Etcheverry
Rif A. Saurous
Ben Laurie
James Manyika
Blaise Agüera y Arcas
Blake A. Richards
While traditional evolutionary algorithms hard-code reproduction, self-replication can emerge spontaneously within digital ``primordial soup… (see more)s''. This paper investigates the co-evolution of this emergent self-replication alongside problem-solving capabilities. We initialize a population of random 32-byte Z80 assembly programs, requiring self-replication to arise purely through random assembly-level mutations and pairwise program interactions. To link these behaviors, we introduce a task-based validation step: correctly evaluating a polynomial raises a program's interaction probability above a baseline rate. Our experiments yield four primary findings. First, self-replication and mathematical problem-solving successfully co-evolve from initial randomness. Second, the pressure to compute accelerates the emergence of compact, robust reproductive architectures that preserve memory for task execution. Third, applying metabolic constraints increases the likelihood that programs evolve conditional halting, terminating early during validation while bypassing the halt during interaction to execute block-copy replication. Finally, when programs are partitioned into spatial task niches, spontaneous self-replication generates an emergent learning curriculum, utilizing simple solutions as stepping stones toward complex polynomials. Altogether, these results demonstrate an interactive feedback loop: environmental task demands actively shape the physical architecture of self-replication, while spontaneous replication alters the evolutionary trajectory of functional problem-solving.
Density Evolution of Soft-Decision Collapsed Projection-Aggregation Decoding for Reed-Muller Codes over the BIAWGN Channel
Jiajie Li
Marvin Rübenacke
Warren J. Gross
Reed-Muller (RM) codes have been shown to achieve capacity over a range of channels, and recently proposed projection-aggregation (PA) decod… (see more)ing has been experimentally shown to achieve near-maximum-likelihood decoding performance. These recent achievements motivate theoretical research on PA decoding. In this work, we analyze the density function of the soft output from collapsed projection-aggregation (CPA) decoding for RM codes over the binary-input additive white Gaussian noise (BIAWGN) channel. We prove that soft-decision CPA decoding returns an exact marginal probability and is symmetric. Based on the analysis, we build a density evolution model for CPA decoding. To simplify the density evolution, we approximate the projection and the fast Hadamard transform decoding using hard-decision decoding. Simulation results over the BIAWGN channel show that our proposed density evolution model captures the fast reduction in the mean and the variance of the soft information returned from the CPA decoding, which qualitatively explains the decoding mechanism and the fast convergence speed of the CPA decoding. We perform an asymptotic analysis based on the proposed density evolution, and we show that CPA decoding can achieve a vanishing error probability for RM codes with a vanishing code rate.
Exploring Test-time Scaling via Prediction Merging on Large-Scale Recommendation
Fuyuan Lyu
Z Chen
Jingyan Jiang
Lingjie Li
Xing Tang
xiuqiang He
Xue Liu
Inspired by the success of language models (LM), scaling up deep learning recommendation systems (DLRS) has become a recent trend in the com… (see more)munity. All previous methods tend to scale up the model parameters during training time. However, how to efficiently utilize and scale up computational resources during test time remains underexplored, which can prove to be a scaling-efficient approach and bring orthogonal improvements in LM domains. The key point in applying test-time scaling to DLRS lies in effectively generating diverse yet meaningful outputs for the same instance. We propose two ways: One is to explore the heterogeneity of different model architectures. The other is to utilize the randomness of model initialization under a homogeneous architecture. The evaluation is conducted across eight models, including both classic and SOTA models, on three benchmarks. Sufficient evidence proves the effectiveness of both solutions. We further prove that under the same inference budget, test-time scaling can outperform parameter scaling. Our test-time scaling can also be seamlessly accelerated with the increase in parallel servers when deployed online, without affecting the inference time on the user side. Code is available here. https://github.com/aTitye/TTS4CTR.
Practical Source Code Recovery from Binary Functions Using Anchor-Based Retrieval and LLM Reasoning
Charles Edward Gagnon
Steven H. H. Ding
Philippe Charland
Benjamin C. M. Fung
We present a practical pipeline for recovering source code from stripped binary functions by combining reverse engineering, anchor-based sou… (see more)rce code retrieval, and large language model reasoning. Our binary-to-source-code retrieval method attempts to identify the source function from a source code database, rather than generating approximate decompiled pseudocode. It extracts anchors such as strings, constants, external calls, and available function names using Ghidra, retrieves candidate files via an inverted-index search database, narrows candidates to likely function snippets, and re-ranks them with a large language model (LLM) based on disassembly, decompiled code, and source metadata. Confident matches can also serve as anchors in later passes. In an evaluation backed by our high-fidelity source code database on a stripped, optimized tcpdump binary, our proposed binary-to-source matching method achieves 95.2% assembly instruction coverage. Experiments on a GitHub-based retrieval database showed lower performance with 35.5% instruction coverage on average, mainly due to retrieval misses. These results show that source-level binary recovery excels with high-quality databases and remains a useful tool in noisy environments.
D-CLIPSE: Distributed Consensus-based Localization with Passive Listening on Shared State Exchange
Multi-robot localization that is accurate and consistent is imperative for downstream tasks such as planning and control. Centralized filter… (see more)ing approaches optimally fuse all available sensor measurements of the team. However, a centralized solution is rarely implementable due to hardware, communication, and computational constraints. Distributed approaches deploy a filter on each robot to estimate their own state and neighbours' states using inter-robot communication. This paper proposes a consistent, communication-efficient, and consensus-based distributed filtering framework that shares both preintegrated odometry and relevant shared states among communicating robots. The proposed method is validated in simulated and experimental scenarios, showing near centralized performance in accuracy, and especially in consistency, compared to the current state-of-the-art decentralized approach.
Equilibrando Reforma e Realidade: Promessas e Armadilhas do Projeto de Lei de Alteração da Lei de Arbitragem e Conciliação de 2024 – Um Estudo do Marco Arbitral Indiano
Rajneesh Kumar
M. Shamima Parveen
Gurminder Kaur
Hrishikesh Manu
The draft Arbitration and Conciliation (Amendment) Bill, 2024 (hereinafter “Draft Bill”) is a significant step in India’s ongoing camp… (see more)aign to enact legislation on modern lines and in harmony with contemporary international practices. The Draft Bill is considered a major legislative reform aimed at expediting procedures, minimising delays, and curbing undue judicial interference, thereby complementing India’s efforts to become an arbitration-friendly destination. Despite these objectives, significant doctrinal, procedural and institutional uncertainties arise from the proposed amendments, raising questions about whether the reforms will achieve their stated goals. This article seeks to map the changes proposed by the Draft Bill and place them in the broader context of India’s arbitration law reform. It analyses the transformative potential of the proposed changes for India’s dispute-resolution landscape vis-à-vis international benchmarks. The study adopts a doctrinal and analytical methodology, drawing on statutory analysis, judicial precedents and comparative international arbitration practices. The analysis finds that the Draft Bill strengthens efficiency and institutionalisation in several respects. However, specific proposals risk generating fresh ambiguities and procedural fragmentation if not carefully implemented. It also attempts to present focused suggestions for refining the implementation of the rescue provisions, maintaining procedural autonomy, popularising institutional arbitration, and aligning arbitration practice with related dispute-resolution mechanisms. It demonstrates that the success of the reforms will hinge upon the effective execution of policy and the translation of legal intent into actual arbitral practice. In this manner, the reforms may help India achieve its ambition to become a global arbitration hub.
Parallel versions of the mesh adaptive direct search algorithm
Sébastien Le Digabel
Christophe Tribes
This work surveys the different parallel variants of the mesh adaptive direct search (MADS) algorithm for constrained blackbox optimization.… (see more) These problems can inherently imply high computational costs due to the possible large number of variables and multi-modality of the search space. In addition, the potential time-intensive nature and time heterogeneity of the blackboxes defining the problem prompts the need for efficient implementations. Parallelism emerges as an actionable solution to mitigate computation time, as modern computer systems rely on multi-core architecture. The reviewed methods employ diverse levels of parallelism and distinct parallel strategies to effectively tackle each aspect outlined above. The manuscript details the practical implementations, provides computational results, and offers insights into the advantages and limitations of each MADS parallel method.
SafeExplorer: An Unbiased Policy Gradient for Reinforcement Learning with Recovery Interventions
Training reinforcement-learning agents directly on physical robots makes every fall costly, since a fall can damage the platform and cannot … (see more)be undone like a simulator reset; the goal is therefore to minimize falls during training rather than trade them off against return, as constrained Markov decision process (MDP) formulations do. A standard mitigation hands control to a separate recovery policy whenever the agent leaves a designer-specified safe region (a subset of state space it should stay within), but the resulting mixed-policy rollouts silently bias every on-policy update, and the importance-sampling correction that would remove this bias is ill-defined whenever the recovery policy is deterministic. We address this bias with a drop-in modification of proximal policy optimization (PPO). Its core is an unbiased policy-gradient estimator that uses the score function only at safe timesteps and never evaluates the recovery policy's density, so it stays valid even when the recovery policy is deterministic, exactly where importance sampling breaks, and it empirically dominates importance sampling even when the recovery policy is stochastic. Because the recovery policy still makes credit assignment slow near the safe-region boundary, two further components accelerate learning: a closed-form value for recovery-triggering states when dynamics and recovery are deterministic, and an imitation loss that copies recovery actions only when recovery succeeds. On a three-environment, five-seed benchmark, the resulting algorithm reduces training-time falls by factors of 233x, 48x, and 26x on HalfCheetah, Ant, and Unitree Go1 over standard PPO, while matching or exceeding PPO's final reward, and on Ant, where the recovery policy is unreliable, it is the only method that reaches 80% of the best final reward.
The 2026 Singapore Consensus on Global AI Safety Research Priorities
Mohan Kankanhalli
Lee Wan Sie
Chris Meserole
Luke Ong
Stuart Russell
Dawn Song
Max Tegmark
Brian Tse
Xue Lan
Andrew Yao
Zhang Ya-Qin
Zhou Bowen
Stephen Casper
Oskar Galeev
Ima (Imane) Bello
Kwan Yee Ng
Vanessa Wilfred … (see 100 more)
Erica Liaw
Lee Chein Inn
Lin Wanxuan
Ng En Qi
Jonathan Lee
José Villalobos
Abhishek Aggarwal
Adam Gleave
Alex Leung
Alvin Kwock
Anthony Tung
Arisa Siong
Arthur Tea
BEN BUCKNALL
Benjamin Weinstein-Raun
He Bing Sheng
Liu Bo
Bryan Kian Hsiang Low
Chris Ngo
Clement Neo
Cyrus Hodes
Dan Hendrycks
Daniel Ross
Liu Dapeng
Denise Wong
Djordje Žikelić
Elham Tabassi
Fabien Le Voyer
Fazl Barez
Gabriel Nicholas
Henry Papadatos
Jaan Tallinn
James Petrie
Xu Jia
Shao Jing
Jonathan Barry
Julia Chen
Sun Jun
Karson Elmgren
Kat Lyness
Katherine Lee
Kristy Loke
Lee Kwee Geak
Leslie Teo
Meng Ling Yu
Lisa Soder
Madhulika Srikumar
Malcolm Murray
Mark Brakel
Mark Nitzberg
Mary Phuong
Matthew Jagielski
Max Fenkell
Miro Plueckebaum
Kim Myuhng Joo
Hu Naying
Neil Davison
Nicolas Miailhe
Niki Iliadis
Nur Syahidah Sahrom
Ong Chen Hui
Pradeep Varakantham
Rebecca Finlay
Renata Dwan
Robert Opp
Rumman Chowdhury
Saad Siddiqui
Sabina Nong
Sam Ramadori
Sami Jawhar
Samuel Boger
Sara Hooker
Ying Shao Wei
Sebastian Hallensleben
Shinyuk Kang
Sophie Toura
Sreejith Balakrishnan
Stephanie Kasaon
Stephen Clare
Summer Yue
Sunny Yuqing Sun
Supheakmungkol Sarin
Tian Tian
Tim Schreier
Tori Westerhoff
Urvashi Aneja
Wayne Tee
Lu Wei
Xu Wei
Zhang Wenxuan
Hu Xia
Yang Xiaofang
Pan Xudong
Xiao Yajun
Yifan Jia
Tan Yong Khiam
Yuejin Du
Yuma Kurihara
Tan Zhi Xuan
Frontier AI capabilities and autonomy are advancing rapidly. A growing number of real-world incidents make a trusted AI ecosystem essential … (see more)to embracing AI with confidence. The 2026 Singapore Consensus is an outcome of the second International Scientific Exchange on AI Safety, bringing together over 100 contributors spanning 13 countries from frontier developers, government safety institutes, academia, and civil society. Building on the 2025 report, it presents a global understanding of technical AI safety research problems of top priority, now with a dedicated focus on societal resilience and on managing the risks of increasingly autonomous AI agents.