Existing fair multi-view clustering methods typically suffer from a severe trade-off between clustering utility and fairness, while incurring prohibitive quadratic complexity on large-scale datasets. To address these challenges, we propose Causal Disentangled Anchor Learning (CDAL), a novel framework that achieves scalable fairness via structural disentanglement. Guided by a structural causal model perspective, CDAL utilizes a dual-anchor mechanism to structurally separate latent representations into orthogonal semantic and sensitive subspaces. We further ensure statistical independence through a linearized Hilbert-Schmidt Independence Criterion (HSIC) constraint, which is optimized via an efficient alternating scheme. Theoretically, we prove the identifiability of the disentangled factors and guarantee the algorithm's global convergence and linear time complexity $\mathcal{O}(n)$. Extensive experiments on large-scale benchmarks demonstrate that CDAL outperforms state-of-the-art methods, achieving a superior utility-fairness trade-off.
论文检索
输入标题、作者或关键词，从 2,854 篇学术成果中精准定位
Applications · Health / Medicine
Integrating language models (LMs) in healthcare systems holds great promise for improving medical workflows and decision-making. However, a critical barrier to their real-world adoption is the lack of reliable evaluation of their trustworthiness, especially in multilingual healthcare settings. Existing LMs are predominantly trained in high-resource languages, making them ill-equipped to handle the complexity and diversity of healthcare queries in mid- and low-resource languages, posing significant challenges for deploying them in global healthcare contexts where linguistic diversity is key. In this work, we present \textsc{Clinic}, a \textbf{C}omprehensive Mu\textbf{l}tilingual Benchmark to evaluate the trustworth\textbf{i}ness of la\textbf{n}guage models \textbf{i}n health\textbf{c}are. \name systematically benchmarks LMs across five key dimensions of trustworthiness: truthfulness, fairness, safety, robustness, and privacy, operationalized through 18 diverse tasks, spanning 15 languages (covering all the major continents), and encompassing a wide array of critical healthcare topics like disease conditions, preventive actions, diagnostic tests, treatments, surgeries, and medications. Our extensive evaluation reveals that LMs struggle with factual correctness, demonstrate bias across demographic and linguistic groups, and are susceptible to privacy breaches and adversarial attacks. By highlighting these shortcomings, \name lays the foundation for enhancing the global reach and safety of LMs in healthcare across diverse languages.
Deep Learning · Large Language Models
AI co-scientists are emerging as a useful tool for human researchers, with a crucial ability being proposing a research plan for a given research goal. In this work, we study how to train language models that generate better research plans by leveraging the vast corpus of existing research papers. To collect diverse training data, we automatically extract research goals and goal-specific grading rubrics from papers across domains. We then train models for research plan generation via reinforcement learning, with a frozen copy of the initial policy acting as the grader, using the rubrics to evaluate plans generated by the training policy. To validate this approach, we conduct a human study for machine learning research goals spanning 225 expert hours. The experts prefer plans generated by our finetuned Qwen3-30B-A3B model over the initial model for 70% goals, and over Grok-4-Thinking for 59.6% goals. To assess generality, we also extend our approach to goals from medical papers, and recent arXiv preprints, evaluating with a jury of frontier models. Our finetuning yields 12-22% relative improvements and significant cross-domain generalization, proving effective even in problem settings like medical research where execution feedback is infeasible. Overall, we demonstrate the potential of a scalable training recipe as a step towards improving general AI co-scientists.
Deep Learning · Large Language Models
Reasoning Large Language Models (R-LLMs) have significantly advanced complex reasoning tasks but often struggle with factuality, generating substantially more hallucinations than their non-reasoning counterparts on long-form factuality benchmarks. However, extending online Reinforcement Learning (RL), a key component in recent R-LLM advancements, to the long-form factuality setting poses several unique challenges due to the lack of reliable verification methods. Previous work has utilized automatic factuality evaluation frameworks such as FActScore to curate preference data in the offline RL setting, yet we find that directly leveraging such methods as the reward in online RL leads to reward hacking in multiple ways, such as producing less detailed or relevant responses. We propose a novel reward function that simultaneously considers the factual precision, response detail level, and answer relevance, and applies online RL to learn high quality factual reasoning. Evaluated on six long-form factuality benchmarks, our factual reasoning model achieves an average reduction of 23.1 percentage points in hallucination rate, a 23% increase in answer detail level, and no degradation in the overall response helpfulness.
Applications · Health / Medicine
Reliable medical audio diagnosis demands models that are not only accurate but also honest about their uncertainty. However, fine-tuned models based on small, imbalanced datasets often become overconfident due to norm bias, whereby they rely on feature magnitude rather than semantic alignment. As a theoretical optimum for class-separating geometric structures, Equiangular Tight Frame (ETF) is effective for class-imbalanced and calibration tasks because of its maximal angular separability and geometric fairness. Yet, existing ETF-based methods perform weak when deal with noisy medical data; specifically, the gradient-based rotation results in instability, while the fixed ETFs fail in adapting to drifting prototypes. To solve this, We propose Spherical Procrustes Alignment (SPA), the first method combining spherical constraints with dynamic ETF alignment for medical audio. The SPA includes two branches: 1) the Spherical branch, which normalizes features and weights to eliminate the norm bias, and 2) the Geometric branch, which adapts features, tracks prototypes, and uses Dynamic Procrustes Alignment to align the fixed ETF with the prototypes, generating stable logits. Then a self-alignment mechanism fuses the two branches to jointly optimize the logits. Experiments on ICBHI 2017 and CirCor DigiScope datasets show that the SPA achieves new state-of-the-art results, turning large pre-trained models into reliable and efficient clinical tools without extra inference costs.
Deep Learning · Large Language Models
Deep research agents perform multi-step research to produce long-form, well-attributed answers. However, most open deep research agents are trained on easily verifiable short-form QA tasks via reinforcement learning with verifiable rewards, which does not extend to realistic long-form tasks. We address this with **Reinforcement Learning with Evolving Rubrics (RLER)**, where rubrics are constructed and maintained to *co-evolve* with the policy model during training. This allows the rubrics to incorporate newly explored information from search and contrasting model responses, enabling better fact checking and more discriminative on-policy feedback. Using RLER, we develop **Deep Research Tulu (DR Tulu-8B)**, the first fully open model that is directly trained for open-ended, long-form deep research. Across four long-form deep research benchmarks in science, healthcare, and general domains, DR Tulu-8B substantially outperforms existing open deep research agents (by 15.6% over Tongyi DR on average) and matches or exceeds proprietary deep research agents (by 0.7% over OpenAI DR on average), while being significantly smaller and cheaper per query (1000x cheaper than OpenAI DR per query).
Deep research agents perform multi-step research to produce long-form, well-attributed answers. However, most open deep research agents are trained on easily verifiable short-form QA tasks via reinforcement learning with verifiable rewards, which does not extend to realistic long-form tasks. We address this with **Reinforcement Learning with Evolving Rubrics (RLER)**, where rubrics are constructed and maintained to *co-evolve* with the policy model during training. This allows the rubrics to incorporate newly explored information from search and contrasting model responses, enabling better fact checking and more discriminative on-policy feedback. Using RLER, we develop **Deep Research Tulu (DR Tulu-8B)**, the first fully open model that is directly trained for open-ended, long-form deep research. Across four long-form deep research benchmarks in science, healthcare, and general domains, DR Tulu-8B substantially outperforms existing open deep research agents (by 15.6% over Tongyi DR on average) and matches or exceeds proprietary deep research agents (by 0.7% over OpenAI DR on average), while being significantly smaller and cheaper per query (1000x cheaper than OpenAI DR per query).
Identifying training data of large-scale models is critical for copyright litigation, privacy auditing, and ensuring fair evaluation. However, existing works typically treat this task as an instance-wise identification without controlling the error rate of the identified set, which cannot provide statistically reliable evidence. In this work, we formalize training data identification as a set-level inference problem and propose Provable Training Data Identification (PTDI), a distribution-free approach that enables provable and strict false identification rate control. Specifically, our method computes conformal p-values for each data point using a set of known unseen data and then develops a novel Jackknife-corrected Beta boundary (JKBB) estimator to estimate the training-data proportion of the test set, which allows us to scale these p-values. By applying the Benjamini–Hochberg (BH) procedure to the scaled p-values, we select a subset of data points with provable and strict false identification control. Extensive experiments across various models and datasets demonstrate that PTDI achieves higher power than prior methods while strictly controlling the FIR.
Generative models such as diffusion models and transformers are powerful tools for learning complex data distributions and generating new samples. However, their black-box nature limits interpretability, and the learned distributions may violate side knowledge arising from domain expertise. We represent such side knowledge as probability distributions over noisy functions of the modeled objects and seek to minimally adjust the generative model to satisfy such constraints. Our approach is to optimize the dual of the corresponding constrained optimization problem, encoding the infinite-dimensional dual variable using a neural network. We introduce a simple and efficient score-based method for fitting the parameters of this neural network, and for simulating from the resulting adjusted distribution. We evaluate our approach on a number of synthetic tasks, as well on two real-world problems: a regularized nonparametric maximum likelihood estimation problem, and the incorporation of class-level fairness constraints into image diffusion models.
Social Aspects · Accountability, Transparency, and Interpretability
As generative AI faces intensifying legal challenges, the machine learning community has increasingly relied on *post-hoc mitigation*---especially machine unlearning and inference-time guardrails---to argue for compliance. **This paper argues that such post-hoc mitigation methods cannot retroactively cure liability from unlawful acquisition and training, because compliance hinges on data lineage, not the outputs.** Our argument has three parts. First, unauthorized copying/ingestion can be a legally complete *completed act*, and model weights may operate as *fixed copies* that retain training-derived expressive value, making later filtering beside the point for infringement. Second, *contract* and *tort/unfair-competition* rules---via licenses, terms of service, and anti-free-riding principles---can independently restrict access and use, often bypassing copyright defenses (e.g., fair use or TDM exceptions). Third, since value from protected inputs can persist in weights, remedies such as *unjust enrichment* and *disgorgement* may require stripping gains and, in some cases, reaching the model itself. We therefore argue for a shift from *Post-Hoc Sanitization* to verifiable *Ex-Ante Process Compliance*.
Applications · Social Sciences
The intelligent verdict is essential for handling voluminous demands of E-commerce dispute. Unlike the legal dispute, it necessitates identifying pivotal clues from redundant multimodal evidence chains, relying on informal transaction rules for dispute verdicts. The complex ``clues-dispute" causal logic and flexible verdict rules render existing methods inadequate. Motivated by this, we propose a pioneering task, **E-commerce Dispute Verdict** (EDV), and introduce **VerdictBench**, the first Multimodal Disputes Verdicts Benchmark for E-commerce, to facilitate the intelligent verdicts. Building upon this, we propose **CyberJurors**, a framework that integrates an Individual Verdict Chain-of-Thought (IV-CoT) and Jury Consensus Verdict (JCV) to clarify the dispute logic and regulate the fair verdict process. *For the individual juror*, IV-CoT decomposes the EDV task into a structured reasoning, enabling fine-grained clues perception and explicit causal logic between clues and dispute. *For the collective jury*, JCV simulates multi-round discussion and voting among jurors guided by Verdict Precedents, effectively mitigating individual biases. Extensive experiments on VerdictBench demonstrate that CyberJurors significantly improves verdict accuracy, fairness, and interpretability, outperforming existing MLLMs by up to 9.48\% in accuracy.
Deep Learning · Foundation Models
While multimodal agents can achieve strong performance through fine-tuning, their ability to generalize remains limited in complex real-world tasks such as mobile navigation, where diverse applications, frequent system changes, and customized workflows are common in practice. We argue that a fundamental bottleneck lies in whether an agent possesses sufficient task-specific procedural knowledge to accomplish a given goal. Such procedural knowledge may be provided by the general capabilities of large language models, or obtained from additional external resources such as web search when necessary. Based on this view, we propose Procedure-Aware Multimodal Agent with Meta Reasoning, a framework that explicitly represents task knowledge as natural-language procedures and trains a procedure-aware grounded agent to condition its actions on this knowledge. By learning to leverage procedural knowledge from different sources, our approach enables robust generalization across tasks, applications, interface versions, and multi-app workflows, achieving substantial improvements on challenging Android benchmarks.
Foundation models are increasingly central to high-stakes AI systems, and governance frameworks now depend on evaluations to assess their risks and capabilities. Although general capability evaluations are widespread, social impact assessments covering bias, fairness, privacy, environmental costs, and labor remain uneven. To characterize this landscape, we conduct the first comprehensive analysis of social impact evaluation reporting, examining 186 first-party release reports and 248 third-party evaluation sources, supplemented by developer interviews. We find a stark division of labor: first-party reporting is sparse, often superficial, and declining in areas like environmental impact and bias, while third-party evaluators provide broader, more rigorous coverage of bias, harmful content, and performance disparities. However, only developers can authoritatively report on data provenance, content moderation labor, costs, and infrastructure, yet interviews reveal these disclosures are deprioritized unless tied to product adoption or compliance. Current practices leave major gaps in assessing societal impacts, underscoring the need for policies that mandate developer transparency, strengthen independent evaluation ecosystems, and create shared infrastructure for aggregating third-party evaluations.
Social Aspects · Robustness
In this position paper, we argue that current safety alignment research efforts for large language models are hindered by many intertwined sources of noise, such as small datasets, methodological inconsistencies, and unreliable evaluation setups. This can, at times, make it impossible to evaluate and compare attacks and defenses fairly, thereby slowing research progress. We systematically analyze the LLM safety evaluation pipeline, covering dataset curation, optimization strategies for automated red-teaming, response generation, and response evaluation using LLM judges. At each stage, we identify key issues and highlight their practical impact. We also propose a set of guidelines for reducing noise and bias in evaluations of future attack and defense papers. Lastly, we offer an opposing perspective, highlighting practical reasons for existing limitations. We believe that addressing the outlined problems in future research will improve the field’s ability to generate easily comparable results and make measurable progress.
Deep Learning · Foundation Models
Any-to-any modeling aims to flexibly relate arbitrary modalities within a single system, a requirement that arises across multimodal learning and scientific domains such as ecology and astronomy. However, existing any-to-any approaches are typically trained from scratch using encoder–decoder or diffusion architectures, limiting empirical performance and the use of pretrained models. We investigate decoder-only any-to-any multimodal modeling, which treats all modalities symmetrically and supports arbitrary modalities as inputs and outputs without modality-specific heads, losses, or task pipelines. As a consequence of this unified design, the resulting model MODUS naturally enables chained generation through intermediate modalities, cross-modal consistency verification, and analysis of visual representations by combining semantic and reconstruction features. Across a range of benchmarks, MODUS demonstrates strong out-of-the-box performance and flexible multimodal composition within a single model.
General Machine Learning · Evaluation
Repairing system crashes discovered by kernel fuzzers like Syzkaller is a critical yet underexplored challenge in software engineering. While recent works have introduced Large Language Model (LLM) based agents for Linux kernel crash-resolution, their evaluation benchmarks are usually static and thus, do not capture the evolving nature of the Linux kernel, and suffer from potential data contamination due to LLM knowledge cutoffs. To address the above problem, we present (i) Live-kBench, an evaluation framework for self-evolving benchmarks that continuously scrapes and evaluates agents on freshly discovered kernel bugs, and (ii) kEnv, an agent-agnostic standardized crash-resolution environment for kernel compilation, execution, and feedback. This design decouples agent workflows from heavy-weight execution, enabling fair and scalable comparison across diverse agent frameworks under identical conditions. To this end, we curate an inaugural dataset of 534 Linux kernel bugs and empirically demonstrate a significant performance gap, with agents achieving up to 25% higher equivalent patch rate on bugs fixed before the LLM knowledge cutoff. Using kEnv, we benchmark three state-of-the-art agents, showing that they resolve 74% of crashes on the first attempt (plausible patches); however only ~20% of generated patches closely match developer fixes. Additionally, exposing crash resolution feedback improves crash resolution rate by 29%. Live-kBench provides the community with an evaluation infrastructure for self-evolving benchmarks that is both time and attribute sensitive; complete with a public dashboard to track agent progress on Linux kernel bugs.
Applications · Chemistry, Physics, and Earth Sciences
Molecular dynamics (MD) is a key tool for simulating the dynamical behavior of atomic systems. However, MD is inherently serial, which makes it difficult to increase single-system throughput with concurrent compute. To address this, we introduce **L**angevin **S**peculative **D**ynamics (**LSD**), a distributed and model-agnostic speculative sampler for accelerating MD *without adding relative error*. Inspired by speculative methods in language and diffusion modeling, LSD uses a draft model to propose fast simulation steps and verifies them in parallel with a slower target model, applying a transport map from the draft to the target distribution. We extend speculative sampling to second-order Langevin dynamics, derive the achievable speedup as a function of physical parameters, show that LSD generalizes across different systems and draft-target combinations with a 3-9x speedup, and confirm theoretically and empirically that LSD samples trajectories from the same distribution as its target model.
Social Aspects · Safety
Ensuring the safety of language models (LMs) while maintaining their usefulness remains a critical challenge in AI alignment. Current approaches rely on sequential adversarial training: generating adversarial prompts and fine-tuning LMs to defend against them. We introduce a different paradigm: framing safety alignment as a non-zero-sum game between an Attacker LM and a Defender LM trained jointly via online reinforcement learning. Each LM continuously adapts to the other's evolving strategies, driving iterative improvement. Our method uses a preference-based reward signal derived from pairwise comparisons instead of point-wise scores, providing more robust supervision and potentially reducing reward hacking. Our RL recipe, AdvGame, shifts the Pareto frontier of safety and utility, yielding a Defender LM that is simultaneously more helpful and more resilient to adversarial attacks. In addition, the resulting Attacker LM converges into a strong, general-purpose red-teaming agent that can be directly deployed to probe arbitrary target models.
Social Aspects · Accountability, Transparency, and Interpretability
Text-to-image diffusion models achieve impressive generation quality but inherit and amplify training-data biases, skewing coverage of semantic attributes. Prior work addresses this in two ways. Closed-set approaches mitigate biases in predefined fairness categories (e.g., gender, race), assuming socially salient minority attributes are known a priori. Open-set approaches frame the task as bias identification, highlighting majority attributes that dominate outputs. Both overlook a complementary task: uncovering rare or minority features underrepresented in the data distribution (social, cultural, or stylistic) yet still encoded in model representations. We introduce RAIGen, the first framework, to our knowledge, for unsupervised rare-attribute discovery in diffusion models. RAIGen leverages Matryoshka Sparse Autoencoders and a novel minority metric combining neuron activation frequency with semantic distinctiveness to identify interpretable neurons whose top-activating images reveal underrepresented attributes. Experiments show RAIGen discovers attributes beyond fixed fairness categories in Stable Diffusion, scales to larger models such as SDXL, supports systematic auditing across architectures, and enables targeted amplification of rare attributes during generation.
Theory · Game Theory
We study the problem of fairly allocating indivisible goods to agents in an online setting, where goods arrive sequentially and must be allocated irrevocably. Focusing on the popular fairness notions of envy-freeness, proportionality, and maximin share fairness (and their approximate variants), we investigate how access to future information changes what guarantees are achievable. Without any information, we prove strong impossibility results even for approximate fairness. With normalization information (agents' total values), we provide an algorithm that achieves stronger fairness guarantees than previously known results, and show matching impossibilities for stronger notions. With frequency predictions (value multisets without order), we design a meta-algorithm that lifts a broad class of offline "share-based" guarantees to the online setting, matching the best-known offline bounds. Finally, we provide learning-augmented variants of both models: under noisy totals or noisy frequency predictions, our guarantees are robust and degrade gracefully with the error parameters.