论文检索

Social Aspects · Accountability, Transparency, and Interpretability

MingYu Lu, Soham Gadgil, Chris Lin, Chanwoo Kim, Su-In Lee

As Text-to-Image (T2I) diffusion models are increasingly used in real-world creative workflows, a principled framework for valuing contributors who provide a collection of data is essential for fair compensation and sustainable data marketplaces. While the Shapley value offers a theoretically grounded approach to attribution, it faces a dual computational bottleneck: (i) the prohibitive cost of exhaustive model retraining for each sampled subset of players (i.e., data contributors) and (ii) the combinatorial number of subsets needed to estimate marginal contributions due to contributor interactions. To this end, we propose **SurrogateSHAP**, a retraining-free framework that approximates the expensive retraining game through inference from a pretrained model. To further improve efficiency, we employ a gradient-boosted tree to approximate the utility function and derive Shapley values analytically from the tree-based model. We evaluate SurrogateSHAP across three diverse attribution tasks: (i) image quality for DDPM-CFG on CIFAR-20, (ii) aesthetics for Stable Diffusion on Post-Impressionist artworks, and (iii) product diversity for FLUX.1 on Fashion-Product data. Across settings, SurrogateSHAP outperforms prior methods while substantially reducing computational overhead, consistently identifying influential contributors across multiple utility metrics. Finally, we demonstrate that SurrogateSHAP effectively localizes data sources responsible for spurious correlations in clinical images, providing a scalable path toward auditing safety-critical generative models. Code is available at https://anonymous.4open.science/r/CFG-Attribution-15DD/

Social Aspects · Fairness

Chengbo Zhang, Zhen Yao, Hao Pang, Changcheng Li

Fairness in machine learning prediction has attracted growing attention in recent years. In this article, we propose a causal–inference–based framework for fair prediction, defined through path-specific counterfactual interventions. Instead of imposing fairness via constraints on predictive objectives or model parameters, our approach specifies fairness directly at the level of counterfactual prediction semantics. Given a learned causal graph, we construct a predictive distribution for the outcome $Y$ using a structural causal model and generate counterfactual predictions by selectively intervening on causal paths emanating from sensitive attributes. By allowing or blocking the propagation of sensitive information along designated paths, possibly involving multiple sensitive sources, our framework induces a hierarchy of interpretable fairness notions, generalizing standard path-specific causal semantics. Our empirical experiments demonstrate how different fairness levels can be instantiated and compared in practice.

Deep Learning · Generative Models and Autoencoders

Kaizhen Zhu, Mokai Pan, Zhechuan Yu, Jingya Wang, Jingyi Yu, Ye Shi

Diffusion Bridge and Flow Matching have both demonstrated compelling empirical performance in transformation between arbitrary distributions. However, there remains confusion about which approach is generally preferable, and the substantial discrepancies in their modeling assumptions and practical implementations have hindered a unified theoretical account of their relative merits. We have, for the first time, provided a unified theoretical and experimental validation of these two models. We recast their frameworks through the lens of Stochastic Optimal Control and prove that the cost function of the Diffusion Bridge is lower, guiding the system toward more stable and natural trajectories. Simultaneously, from the perspective of Optimal Transport, interpolation coefficients $t$ and $1-t$ of Flow Matching become increasingly ineffective when the training data size is reduced. To corroborate these theoretical claims, we propose a novel, powerful architecture for Diffusion Bridge built on a latent Transformer, and implement a Flow Matching model with the same structure to enable a fair performance comparison in various experiments. Comprehensive experiments are conducted across Image Restoration, Translation, and Style Transfer tasks, systematically varying both the distributional discrepancy (different difficulty) and the training data size. Extensive empirical results align perfectly with our theoretical predictions and allow us to delineate the respective advantages and disadvantages of these two models. Our code is available at \url{https://anonymous.4open.science/r/DBFM-3E8E/}.

Deep Learning · Large Language Models

Shobhita Sundaram, John Quan, Ariel Kwiatkowski, Kartik Ahuja, Yann Ollivier, Julia Kempe

RL methods for finetuning large reasoning models stall on datasets with low initial success rates, and thus little training signal. We investigate a fundamental question: Can a pretrained LLM leverage latent knowledge to generate an automated curriculum for problems it cannot solve? We explore this with SOAR: A self-improvement framework designed to surface these pedagogical signals through meta-RL. A teacher model proposes synthetic problems for a student model, and is rewarded with its improvement on a subset of hard problems, thus grounding the curriculum in real student progress rather than proxy rewards. Our study on the hardest subsets of math benchmarks (0/128 success) reveal three core findings. First, it is possible to realize bi-level meta-RL that unlocks learning under sparse, binary rewards by sharpening a latent capacity of pretrained models to generate useful problems. Second, grounded rewards outperform intrinsic rewards used in prior LLM self-play, reliably avoiding the typical instability and diversity collapse modes. Third, the structure and well-posedness of questions are more critical for learning progress than solution correctness. Our results suggest that the ability to generate useful stepping stones does not require the preexisting ability to solve the hard problems, paving a principled path to escape reasoning plateaus without additional curated data.

Deep Learning · Large Language Models

Charles Arnal, Vivien Cabannnes, Taco Cohen, Julia Kempe, REMI MUNOS

While Experience Replay—the practice of storing rollouts and reusing them multiple times during training—is a foundational technique in general RL, it remains largely unexplored in LLM post-training due to the prevailing belief that fresh, on-policy data is essential for high performance. In this work, we challenge this assumption. We present a systematic study of replay buffers for LLM post-training, formalizing the optimal design as a trade-off between staleness-induced variance, sample diversity and the high computational cost of generation. We show that strict on-policy sampling is suboptimal when generation is expensive. Empirically, we show that a well-designed replay buffer can drastically reduce inference compute without degrading -- and in some cases even improving -- final model performance, while preserving policy entropy.

Yunzhen Feng, Julia Kempe, Cheng Zhang, Parag Jain, Anthony Hartshorn

Large reasoning models (LRMs) spend substantial test-time compute on long chain-of-thought (CoT) traces, but what *characterizes* an effective CoT remains unclear. While prior work reports gains from lengthening CoTs and increasing review via appended *wait* tokens, recent studies suggest that shorter thinking can outperform longer traces. We therefore conduct a systematic evaluation across ten LRMs on math and scientific reasoning. Contrary to the “longer-is-better” narrative, we find that both naively using longer CoTs and more review behaviors are associated with *lower* accuracy. As CoT unfolds step by step, token-level metrics can conflate verbosity with process quality. We introduce a graph view of CoT to extract structure and identify a single statistic—the *Failed-Step Fraction* (FSF), the fraction of steps in abandoned branches—that consistently outpredicts length and review ratio for correctness across models. To probe causality, we design two interventions. First, we rank candidate CoTs by each metric at test time, where FSF yields the largest pass@1 gains; second, we edit CoTs to remove failed branches, which significantly improves accuracy, indicating that failed branches bias subsequent reasoning. Taken together, these results characterize effective CoTs as those that *fail less* and support *structure-aware* test-time scaling over indiscriminately generating long CoTs.

Reinforcement Learning · Planning

Quentin Garrido, Tushar Nagarajan, Basile Terver, Nicolas Ballas, Yann LeCun, Michael Rabbat

Agents that can reason and plan in the real world must be able to predict the consequences of their actions. World models possess this capability but require action annotations that can be complex to obtain at scale. Latent action models address this issue by learning an action space from videos alone. Our work studies the training of latent action world models on in-the-wild videos, expanding the scope of existing works that focus on simple robotics simulations, video games, or manipulation data. While diverse videos enable modeling richer actions, they introduce challenges of environmental noise and lack of a common embodiment across videos. To address these, we carefully study the design and evaluation of latent actions. We find that constrained continuous latent actions are better suited for complex in-the-wild videos, compared to vector quantization. For example, actions specific to in-the-wild videos such as humans entering the room, can be modeled and then transferred across videos. However, in the absence of a common embodiment, learned latent actions are localized in space, relative to the camera. Nonetheless, we are able to train a controller that maps known actions to latent ones, allowing us to use latent actions as a universal interface to solve planning tasks on par with action-conditioned baselines.

General Machine Learning · Evaluation

Robin Hesse, Dogukan Bagci, Bernt Schiele, Simone Schaub-Meyer, Stefan Roth

Deep learning has become an essential part of computer vision, with deep neural networks (DNNs) excelling in predictive performance. However, they often fall short in other critical quality dimensions, such as robustness, calibration, or fairness. While existing studies have focused on a subset of these quality dimensions, none have explored a more general form of "well-behavedness" of DNNs. With this work, we address this gap by simultaneously studying nine different quality dimensions for image classification. Through a large-scale study, we provide a bird's-eye view by analyzing 326 backbone models and how different training paradigms and model architectures affect these quality dimensions. We reveal various new insights such that (i) vision-language models exhibit high class balance on ImageNet-1k classification and strong robustness against domain changes; (ii) training models initialized with weights obtained through self-supervised learning is an effective strategy to improve most considered quality dimensions; and (iii) the training dataset size is a major driver for most of the quality dimensions. We conclude our study by introducing the QUBA score (Quality Understanding Beyond Accuracy), a novel metric that ranks models across multiple dimensions of quality, enabling tailored recommendations based on specific user needs.

Reinforcement Learning · Everything Else

Xiaoxuan Wang, Han Zhang, Haixin Wang, Yidan Shi, Ruoyan Li, Kaiqiao Han, Chenyi Tong, Haoran Deng, Alexander Taylor, Renliang Sun 等

Agentic reinforcement learning (ARL) has rapidly gained attention as a promising paradigm for training agents to solve complex, multi-step interactive tasks. In this paper, we first propose $\textbf{ARLArena}$, a fair and systematic analysis framework that encompasses a broad spectrum of ARL algorithms and decomposes policy optimization (PO) through multiple policy gradient dimensions. Through this fine-grained analysis, we distill a unified perspective on ARL and, guided by the identified governing factors, propose $\textbf{SAMPO}$, a stable agentic PO method designed to mitigate the dominant sources of instability in ARL. Empirically, SAMPO achieves consistently stable training and strong performance across diverse agentic tasks. Overall, this study provides a unifying policy gradient perspective for ARL and offers practical guidance for building stable and reproducible LLM-based agent training pipelines. Our codebase is open-sourced at https://anonymous.4open.science/r/SAMPO-02B3.

Deep Learning · Large Language Models

Mickel Liu, Liwei Jiang, Yancheng Liang, Simon Du, Yejin Choi, Tim Althoff, Natasha Jaques

Conventional large language model (LLM) safety alignment relies on a reactive, disjoint loop: attackers exploit a static model, then defenders patch exposed vulnerabilities. This sequential setup leads to attackers overfitting obsolete exploits while defenders perpetually lag behind emerging threats. To address this, we introduce Self-RedTeam, the first fully online self-play multi-agent reinforcement learning (MARL) algorithm that continuously co-evolves attacker and defender for robust safety alignment. A single policy self-plays as both attacker and defender, generating adversarial prompts and defending against them, with a reward model adjudicating outcomes. Each role uses hidden chain-of-thought for strategic planning. Grounded in two-player zero-sum game theory, we establish a theoretical safety guarantee: if the game converges to Nash Equilibrium, the defender produces safe responses against any adversarial input. Empirically, Self-RedTeam generalizes across five models from the Llama and Qwen families, uncovering more diverse attacks (+17.80% SBERT) and improving safety of RLHF-trained models by up to 95% across 14 benchmarks. Our work motivates a shift from reactive patching to proactive co-evolution, enabling LLM safety self-improvement via online self-play MARL.

Social Aspects · Fairness

Zachary Lazri, Anirudh Nakra, Ivan Brugere, Danial Dervovic, Antigoni Polychroniadou, Furong Huang, Dana Dachman-Soled, Min Wu

Algorithmic fairness is often studied in static or single-agent settings, yet many real-world decision-making systems involve multiple interacting entities whose multi-stage actions jointly influence long-term outcomes. Existing fairness methods applied at isolated decision points frequently fail to mitigate disparities that accumulate over time. Although recent work has modeled fairness as a sequential decision-making problem, it typically assumes centralized agents or simplified dynamics, limiting its applicability to complex social systems. We introduce **MAFE**, a suite of *Multi-Agent Fair Environments* designed to simulate realistic, modular, and dynamic systems in which fairness emerges from the interplay of multiple agents. We demonstrate MAFEs in three domains—loan processing, healthcare, and higher education—supporting heterogeneous agents, configurable interventions, and fairness metrics. The environments are open-source and compatible with standard multi-agent reinforcement learning (MARL) libraries, enabling reproducible evaluation of fairness-aware policies. Through extensive experiments on cooperative use cases, we demonstrate how MAFE facilitates the design of equitable multi-agent algorithms and reveals critical trade-offs between fairness, performance, and coordination. MAFE provides a foundation for systematic progress in dynamic, multi-agent fairness research.

Theory · Game Theory

Haris Aziz, Ling Gai, Yuhang Guo, Jeremy Vollen

We study the transit stop placement (TrSP) problem in general metric spaces, where agents travel between source–destination pairs and may either walk directly or utilize a shuttle service via selected transit stops. We investigate fairness in TrSP through the lens of justified representation (JR) and the core, and uncover a structural correspondence with fair clustering. Specifically, we show that a constant-factor approximation to proportional fairness in clustering can be used to guarantee a constant-factor bi-parameterized approximation to core. We establish a lower bound of $1.366$ on the approximability of JR, and moreover show that no clustering algorithm can approximate JR within a factor better than $3$. Going beyond clustering, we propose the Expanding Cost Algorithm, which achieves a tight $2.414$-approximation for JR, but does not give any bounded core guarantee. In light of this, we introduce a parameterized algorithm that interpolates between these approaches, and enables a tunable trade-off between JR and core. Finally, we complement our results with an experimental analysis using small-market public carpooling data.

Deep Learning · Large Language Models

Yuda Song, Lili Chen, Fahim Tajwar, REMI MUNOS, Deepak Pathak, J. Bagnell, Aarti Singh, Andrea Zanette

The success of RL for LLM post-training stems from an unreasonably uninformative source: a single bit of information per rollout as binary reward or preference label. At the other extreme, distillation offers dense supervision but requires demonstrations, which are costly and difficult to scale. We study natural language feedback as an intermediate signal: richer than scalar rewards, yet cheaper than complete demonstrations. Textual feedback is a natural mode of human interaction and is already abundant in many real-world settings, where users, tools, and automated judges routinely critique LLM outputs. Towards leveraging text feedback at scale, we formalize a multi-turn RL setup where text feedback is available during training but not at inference. Therefore, models must learn to internalize the feedback in order to improve their test-time single-turn performance. To do this, we propose two methods: Self Distillation, which trains the single-turn policy to match its own feedback-conditioned second-turn generations; and Feedback Modeling, which predicts the feedback as an auxiliary objective. We provide theoretical analysis on both methods, and empirically evaluate on reasoning puzzles, competition math, and creative writing tasks. Our results show that both methods consistently outperform strong baselines across benchmarks, highlighting the potential of RL with an additional source of rich supervision at scale.

Social Aspects · Safety

Maya Okawa

Multi-agent LLM debates achieve strong performance on decision-making tasks as well as problem-solving benchmarks, yet their safety and fairness risks remain poorly understood. Notably, interaction can amplify the biases of single LLMs, raising concerns for real-world deployment. We identify the emergence of collective (often biased) norms in multi-agent LLM debates and show that noise (e.g., LLM sampling temperature) is a key driver. To explain this, we propose an analytical framework drawing on physics-inspired theoretical models of social dynamics. We predict a phase transition to collective bias when conformity surpasses a critical threshold given the LLMs' initial bias and debate noise. We test the theoretical predictions through controlled experiments and observe a finite-size crossover consistent with an underlying phase transition. We further find that agent heterogeneity suppresses emergence by smoothing (rounding) this transition. Finally, we show that these insights generalize to realistic decision-making tasks, including investment decisions and LLM-as-a-judge evaluation.

Social Aspects · Alignment

Kaizhao Liu, Qi Long, Zhekun Shi, Weijie Su, Jiancong Xiao

Aligning large language models (LLMs) with diverse human preferences is critical for ensuring fairness and informed outcomes when deploying these models for decision-making. In this paper, we seek to uncover fundamental statistical limits concerning aligning LLMs with human preferences, with a focus on the probabilistic representation of human preferences and the preservation of diverse preferences in aligned LLMs. We first show that human preferences can be represented by a reward model if and only if the preference among LLM-generated responses is free of any Condorcet cycle. Moreover, we prove that Condorcet cycles exist with probability converging to one exponentially fast under a general probabilistic preference model called the Luce model, thereby demonstrating the impossibility of fully aligning human preferences using reward-based approaches such as reinforcement learning from human feedback. Next, we explore the conditions under which LLMs would employ mixed strategies -- meaning they do not collapse to a single response -- when aligned in the limit using a non-reward-based approach, such as Nash learning from human feedback. We identify a necessary and sufficient condition for mixed strategies: the absence of a response that is preferred over all others by a majority. As a blessing, we prove that this condition holds with high probability under the Luce model, thereby highlighting the statistical possibility of preserving minority preferences without explicit regularization in aligning LLMs.

Social Aspects · Accountability, Transparency, and Interpretability

Gengrui (Edward) Zhang

GenAI systems, particularly LLMs, rely heavily on vast amounts of publicly available digital content as training data. A significant portion of this content is protected by copyright. While large-scale data scraping may be lawful under certain jurisdictions, the use of copyrighted works to generate outputs that compete with or replicate original creations raises unresolved legal, economic, and ethical concerns. In this position paper, we argue that data providers should be fairly compensated based on their measurable contribution to inference-time outcomes, rather than through coarse, one-time licensing or blanket agreements. We examine alternative perspectives on data ownership, fair use, and model training, and discuss why existing approaches fail to align incentives between GenAI developers and content creators. We then outline concrete roadmaps for developing decentralized systems that enable contribution-aware revenue sharing, including mechanisms for attribution, accounting, and payout at scale. We argue that fair revenue distribution for data providers will not only help resolve ongoing legal disputes surrounding GenAI systems, but also foster a new era of collaboration, rather than competition, between model developers and data creators. By incentivizing the production and sharing of high-quality datasets, such mechanisms can ultimately accelerate the development of more robust, trustworthy, and socially sustainable GenAI systems.

Probabilistic Methods · Monte Carlo and Sampling Methods

Aaron Havens, Brian Karrer, Neta Shaul

Sampling from unnormalized densities is analogous to the generative modeling problem, but the target distribution is defined by a known energy function instead of data samples. Evaluating the energy function is often costly, and thus a primary challenge is to learn an efficient sampler. We introduce *Flow Sampling*, a framework built on diffusion models and flow matching for the data-free setting. Our training objective is conditioned on a noise sample and regresses onto a *denoising* diffusion drift constructed from the energy function. In contrast, diffusion models' objective is conditioned on a data sample and regresses onto a *noising* diffusion drift. We utilize the interpolant process to minimize the number of energy function evaluations during training, resulting in an efficient and scalable method for sampling unnormalized densities. Furthermore, our formulation naturally extends to Riemannian manifolds, enabling diffusion-based sampling in geometries beyond the Euclidean space. We derive a closed-form formula for the conditional drift on constant curvature manifolds, including hyperspheres and hyperbolic spaces. We evaluate Flow Sampling on synthetic energy benchmarks, large-scale amortized molecular conformer generation, and distributions supported on the sphere, demonstrating strong empirical performance.

Applications · Computer Vision

Ye Zhu, Kaleb Newman, Johannes Lutzeyer, Adriana Romero-Soriano, Michal Drozdzal, Olga Russakovsky

Despite high semantic alignment, modern text-to-image (T2I) generative models still struggle to synthesize diverse images from a given prompt. This lack of diversity not only restricts user choice, but also risks amplifying societal biases. In this work, we enhance the T2I diversity through a geometric lens. Unlike most existing methods that rely primarily on entropy-based guidance to increase sample dissimilarity, we introduce Geometry-Aware Spherical Sampling (GASS) to enhance diversity by explicitly controlling both prompt-dependent and prompt-independent sources of variation. Specifically, we decompose the diversity measure in CLIP embeddings using two orthogonal directions: the text embedding, which captures semantic variation related to the prompt, and an identified orthogonal direction that captures prompt-independent variation (e.g., backgrounds). Based on this decomposition, GASS increases the geometric projection spread of generated image embeddings along both axes and guides the T2I sampling process via expanded predictions along the generation trajectory. Our experiments on different frozen T2I backbones (U-Net and DiT, diffusion and flow) and benchmarks demonstrate the effectiveness of disentangled diversity enhancement with minimal impact on image fidelity and semantic alignment.

Guibin Zhang, Haotian Ren, Chong Zhan, Junhao Wang, He Zhu, Wangchunshu Zhou, Shuicheng YAN

Self-evolving memory systems are rapidly reshaping the evolutionary paradigm of large language model (LLM)-based agents. Prior work has predominantly relied on manually engineered memory architectures to store trajectories, distill experience, and synthesize reusable tools, enabling agents to evolve on the fly within environment interactions. However, this paradigm is fundamentally constrained by the \textit{staticity} of the memory system itself: while memory facilitates agent-level evolving, the underlying memory architecture cannot be meta-adapted to diverse task contexts. To address this gap, we propose MemEvolve, a meta-evolutionary framework that jointly evolves agents’ experiential knowledge and their memory architecture, allowing agent systems not only to accumulate experience but also to progressively refine how they learn from it. To ground MemEvolve in prior work and promote openness in future self-evolving systems, we introduce EvolveLab, a unified memory codebase that distills twelve representative memory systems into a modular design space (\textit{encode}, \textit{store}, \textit{retrieve}, \textit{manage}), providing a standardized implementation substrate and a fair experimental arena. Extensive evaluations on four challenging agentic benchmarks show that MemEvolve delivers (i) substantial performance gains, improving frameworks such as SmolAgent and Flash-Searcher by up to $17.06\%$, and (ii) strong cross-task and cross-LLM generalization, yielding memory architectures that transfer effectively across diverse benchmarks and backbones.

Deep Learning · Generative Models and Autoencoders

Abhi Gupta, Polina Barabanshchikova, Vikas Garg, Samuel Kaski, Tommi Jaakkola

With the widespread availability of pre-trained diffusion models, there are many options for which models to use and how to use them together. Making these decisions depends highly on both the user's goals and the expertise of each model. Taking this into account, we propose coordinating models as one would a specialized workforce--through a fair yet efficient division of labor. Divide-and-Denoise uses multiple pre-trained diffusion models, each defined over the same space, to refine a noisy sample over time. At every timestep, we alternate between (i) dividing the sample into regions in a way that satisfies our game-theoretic criteria and (ii) denoising a region with the assigned model in a way that respects our alignment criteria. This leads to a new composite denoising process that evolves together with a division process. Since ground truth for how models should interact is typically not available in our setup, we measure how well Divide-and-Denoise coordinates a team of single-concept text-to-image diffusion models relative to a multi-concept model. Across several image quality metrics including the GenEval benchmark, our method generates images that capture the strengths of each model, outperforming baselines and resolving common failures like missing objects and mismatched attributes.