论文检索

Social Aspects · Accountability, Transparency, and Interpretability

Ted Fujimoto, Benz

The advancement of AI capabilities compels researchers and the public to be more aware of its potential worldwide impact. A pressing near-term concern is the regulation of military AI applications. Armament manufacturers and defense contractors are increasingly investing in AI capabilities and forging partnerships with AI companies, creating a burgeoning coalition that demands military leaders, arms control diplomacy experts, and AI researchers collaborate to ensure a safer future. While AI researchers often focus on the long-term implications of superintelligent AI, this approach may not adequately address the immediate challenges posed by AI in military applications. Success requires acknowledging and mitigating the emerging risks of frontier AI models that plan to be applied defense applications, like military AI systems. Arms control has reduced past catastrophic risks, so lessons learned from nuclear deterrence can guide AI safety and security research towards innovations in verification and diplomacy. AI researchers, however, must assist in leading the technical research that clearly defines and alleviates instability in military settings. Given these new responsibilities and the lack of sufficiently reliable solutions, we argue that AI researchers must take a leading role in advancing arms control research to minimize risk in military AI applications.

General Machine Learning · Evaluation

Jinyu Liu, Xincheng Shuai, Henghui Ding, Yu-Gang Jiang

Unified multimodal models capable of both understanding and generation have achieved remarkable strides. However, despite their unified designs, existing evaluations typically assess understanding and generation capabilities in isolation, overlooking the synergy between comprehension and generation. To bridge this gap, we introduce **Unison**, a comprehensive benchmark comprising 2,169 high-quality unified task samples, designed to evaluate joint understanding and generation in unified multimodal models. Unison offers three key strengths: **1) Comprehensive Dimensions**: Unison encompasses internal consistency, understanding-guided generation, generation-guided understanding, and mutual enhancement to enable holistic evaluation. **2) Diagnostic Evaluation**: it provides both unified and decoupled tracks for understanding and generation, allowing fine-grained attribution of failure modes and quantitative analysis of the gains from unified modeling. **3) Human Alignment**: we also train Unison-Judge, an evaluation model well aligned with human judgments to achieve reliable assessment. Based on systematic evaluations of state-of-the-art models on Unison, we uncover critical limitations in current unified multimodal systems and highlight promising directions for future research. Unison will be publicly released to facilitate evaluation and advance this field.

General Machine Learning · Evaluation

Tom Sühr, Florian Dorner, Olawale Salaudeen, Augustin Kelava, Samira Samadi

Large Language Models (LLMs) have achieved remarkable results on a range of standardized tests originally designed to assess human cognitive and psychological traits, such as intelligence and personality. While these results are often interpreted as strong evidence of human-like characteristics in LLMs, this paper argues that such interpretations constitute an ontological error. Human psychological and educational tests are theory-driven measurement instruments, calibrated to a specific population. Applying these tests to non-human subjects without empirical validation, risks mischaracterizing what is being measured. Furthermore, a growing trend frames AI performance on benchmarks as measurements of traits such as ``intelligence'', despite known issues with validity, data contamination, cultural bias and sensitivity to superficial prompt changes. We argue that interpreting benchmark performance as measurements of human-like traits, lacks sufficient theoretical and empirical justification. This leads to our position: Stop Evaluating AI with Human Tests, Develop Principled, AI-specific Tests instead. We call for the development of principled, AI-spec by laying out, end-to-end, how valid measurement instruments are constructed and validated and where the ontological error enters when a human-calibrated instrument is applied to LLMs.

Theory · Learning Theory

Jingda Wu, Changxiao Cai

Score-based diffusion models have demonstrated remarkable empirical success in learning high-dimensional distributions, particularly those exhibiting low-dimensional and multi-modal structures. However, theoretical understanding of their statistical efficiency remains limited. Existing theories typically rely on strong regularity assumptions, such as uniformly bounded densities or globally smooth score functions, which fail to capture such intrinsic structures. In this work, we study the sample complexity of diffusion models in learning distributions supported on a union of low-dimensional subspaces. Assuming that data within each subspace follows a subgaussian distribution, we show that diffusion models require at most $\widetilde{O}(\varepsilon^{-k \vee 2})$ samples to achieve $\varepsilon$ error in 1-Wasserstein distance, where $k$ is the intrinsic dimension. This near-optimal rate depends only on the intrinsic dimension and significantly improves upon prior works that suffer from the curse of dimensionality. Notably, our analysis applies to a broad collection of distributions without requiring smoothness or log-concavity assumptions. These results provide rigorous evidence for the effectiveness of diffusion models in learning low-dimensional, multi-modal distributions.

Applications · Chemistry, Physics, and Earth Sciences

Chenhui Xu, Fuxun Yu, Michael Bianco, Jacob Kovarskiy, Raphael Tang, Qi Zhang, Zirui Xu, Will LeVine, Brandon Dubbs, Heming Liao 等

Training robust reasoning vision-language models (VLMs) in rare domains (such as geospatial) is fundamentally constrained by supervision scarcity. While raw geospatial imagery is abundant, the amount of task-direct supervision falls far behind that of common domains. In this work, we validate an important conclusion: indirect verifiable rewards, derived from seemingly unrelated metadata, are sufficient to induce sophisticated and generalizable geospatial reasoning across a wide range of downstream tasks (25+). We present Geo-R1 as one empirical instantiation of this paradigm. Rather than relying on limited task-specific annotations (i.e., direct rewards), Geo-R1 utilizes scalable, verifiable indirect proxy rewards based on cross-view alignment with metadata (geolocation information) to drive reinforcement learning at scale. Such indirect rewards successfully motivate the model to discover and internalize zero-shot geospatial reasoning across diverse tasks, achieving extraordinary zero-shot transfer on out-of-distribution benchmarks and even surpassing fully supervised specialists on certain benchmarks. These findings indicate that optimizing for indirect verifiable rewards may provide a scalable pathway to unlock generalized reasoning capabilities in rare domains with massive unlabeled data archives. Our code is available at: \url{https://anonymous.4open.science/r/Geo-R1-ICML}.

Rohit Kumar Salla, Manoj Saravanan, Ramya Amancherla

Late-interaction retrievers like ColBERT achieve high quality but suffer from large multi-vector indices. Standard compression minimizes token reconstruction error, while ranking depends critically on preserving scores of sparse "winner" tokens. We introduce CrossQ which adaptively allocates precision within documents by conditioning token codes on lightweight document context computed at indexing time (but not stored). Trained with ranking-aligned objectives that preserve candidate score distributions and protect hard-negative margins, CrossQ improves MRR@10 by +0.012 on MS MARCO and average nDCG@10 by +0.018 on BEIR over strong baselines at matched footprints (2-8 B/token). With light fine-tuning, CrossQ achieves 61x compression while narrowing the gap with full-precision ColBERT to just 2.3% MRR@10, establishing a new state-of-the-art in the latency-quality tradeoff for memory-constrained retrieval.

Social Aspects · Privacy

Hilal Asi, Hongjie Chen

We study the problem of private hypothesis selection: given samples from an unknown distribution drawn from a finite hypothesis class, the goal is to identify the best hypothesis under the constraint of differential privacy. Existing algorithms for this problem are either computationally expensive or achieve sub-optimal statistical rates. We propose new algorithms that achieve near-optimal rates while running in nearly linear time in the number of hypotheses. Rather than applying the exponential mechanism directly with a score function that requires pairwise comparisons between hypotheses, our approach introduces a carefully designed loss function based on a small set of strong hypotheses. This structure allows the score to be evaluated efficiently for most hypotheses, yielding significant computational savings. We further extend our algorithms to the agnostic setting, where the true distribution may not belong to the hypothesis class. As an application, we obtain faster differentially private algorithms for universal statistical estimation in low dimensional settings.

Applications · Computer Vision

Rishit Dagli, Donglai Xiang, Vismay Modi, Xuning Yang, Gavriel State, David I.W., Maria Shugrina

Accurate mechanical properties (or materials) Young's modulus ($E$), Poisson's ratio ($\nu$) and density ($\rho$) are essential for reliable physics simulation of digital worlds, but most 3D assets lack this information. We propose AdaVoMP, a method for predicting accurate dense spatially-varying $(E, \nu, \rho)$ for input 3D objects across representations, improving the resolution, accuracy, and memory efficiency over the state-of-the-art. The foundation of our technique is a sparse and adaptive voxel structure SAV that efficiently represents both the input 3D shape and the material field output. We replace the fixed-voxel model of the most accurate prior method, VoMP, with a novel sparse transformer encoder-decoder model that learns to generate a unique SAV autoregressively for every input shape to represent its materials, achieving a resolution $16^3\times$ higher than prior art. Experiments show that AdaVoMP estimates more accurate volumetric properties, even with lesser test-time compute than all prior art. This allows us to convert high-resolution complex 3D objects into simulation-ready assets, resulting in realistic deformable simulations.

General Machine Learning · Representation Learning

Florine Hartwig, Josua Sassen, Juliane Braunsmann, Martin Rumpf, Benedikt Wirth

Latent manifolds of autoencoders provide low-dimensional representations of data, which can be studied from a geometric perspective. We propose to describe these latent manifolds as implicit submanifolds of some ambient latent space. Based on this, we develop tools for a discrete Riemannian calculus approximating classical geometric operators. These tools are robust against inaccuracies of the implicit representation often occurring in practical examples. To obtain a suitable implicit representation, we propose to learn an approximate projection onto the latent manifold by minimizing a denoising objective. This approach is independent of the underlying autoencoder and supports the use of different Riemannian geometries on the latent manifolds. The framework in particular enables the computation of geodesic paths connecting given end points and shooting geodesics via the Riemannian exponential maps on latent manifolds. We evaluate our approach on various autoencoders trained on synthetic and real data.

Theory · Optimization

Yiyang Lu, Hareshkumar Jadav, Mohammad Pedramfar, Ranveer Singh, Vaneet Aggarwal

We study online maximization of non-monotone Diminishing-Return(DR)-submodular functions over down-closed convex sets, a regime where existing projection-free online methods suffer from suboptimal regret and limited feedback guarantees. Our main contribution is a new structural result showing that this class is $1/e$-Upper-Linearizable under carefully designed exponential reparametrization, scaling parameter, and surrogate potential, enabling a reduction to online linear optimization. As a result, we obtain optimal $O(T^{1/2})$ static regret with a single gradient query per round and unlock adaptive and dynamic regret guarantees, together with improved rates under semi-bandit, bandit, and zeroth-order feedback. Across all feedback models, our bounds strictly improve the state of the art.

Social Aspects · Accountability, Transparency, and Interpretability

Constantin Venhoff, Iván Arcuschin, Phil Torr, Arthur Conmy, Neel Nanda

Why do thinking language models outperform their base counterparts, and what exactly do they learn during training? We introduce constructive model diffing, a framework for understanding fine-tuned models by explicitly constructing the base-to-fine-tuned difference from interpretable components to produce hybrid models, and measuring how well they recover the fine-tuned model's performance. For thinking models, we decompose the diff into two components: reasoning mechanisms (steering vectors that activate specific behaviors in the base model) and reasoning heuristics (a classifier that determines when each mechanism should fire). To ground this decomposition, we develop an unsupervised methodology using Sparse Autoencoders to discover interpretable taxonomies of reasoning behaviors. Evaluating nine model configurations (five RL-trained, four distilled), we find a striking difference between training methods: the hybrid models for the five RL-trained models achieve much higher performance recovery compared to the four distilled models. This indicates RL-trained models primarily learn sophisticated heuristics for deploying pre-existing base model mechanisms, while distillation affects the mechanisms themselves. These results provide a new lens for understanding what different training paradigms teach, with potential implications for efficient reasoning model development.

Social Aspects · Accountability, Transparency, and Interpretability

Iván Arcuschin, Jett Janiak, Robert Krzyzanowski, Senthooran Rajamanoharan, Neel Nanda, Arthur Conmy

Recent studies indicate that when faced with explicit biases in prompts, models often omit mentioning these biases in their Chain-of-Thought (CoT) output, revealing that verbalized reasoning can give an incorrect picture of how models arrive at conclusions (unfaithfulness). In this work, we show that unfaithful CoT also occurs on naturally worded, non-adversarial prompts without adding artificial biases or editing model outputs. We find that when separately presented with the questions "Is X bigger than Y?" and "Is Y bigger than X?", models sometimes produce superficially coherent arguments to justify systematically answering Yes to both questions or No to both questions, despite such responses being logically contradictory. We present preliminary evidence that this is due to models' implicit biases towards Yes or No, labeling this *Implicit Post-Hoc Rationalization*. Our results reveal rates up to 13% for production models, and while frontier models are more faithful, none are entirely so, including thinking models like DeepSeek R1 (0.37%) and Sonnet 3.7 with thinking (0.04%). We also investigate *Unfaithful Illogical Shortcuts*, where models use subtly illogical reasoning to make speculative answers to hard math problems seem rigorously proven. Our findings indicate that while CoT can be useful for assessing outputs, it is not a complete account of a model's internal reasoning and should be used with caution in agentic or safety-critical settings.

Deep Learning · Attention Mechanisms

Zhigeng Liu, Zhiyuan Ning, Ruixiao Li, Xiaoran Liu, Yuerong Song, Min zhang, Ziwei He, Xipeng Qiu

The development of long-context Large Language Models (LLMs) is constrained by the memory bandwidth bottleneck and quadratic complexity of the attention mechanism during decoding. To overcome the inherent trade-offs between the memory overhead of metadata-based metrics and the computational inefficiency of adaptive selection strategies, we present \textbf{Faster Flash Decoding (FFD)}, a novel hardware-algorithm co-design framework designed to break the memory wall in long-context decoding. FFD integrates the selector and computer into a fully fused kernel, replacing external metadata indices with content-aware scanning via low-bit quantization. Furthermore, we introduce the top-$\delta$ strategy, which dynamically filters blocks to achieve distribution-adaptive sparsity without global synchronization. As a training-free, plug-and-play solution, FFD enables the reuse of scanning results for computation, achieving up to 11.6x kernel-level speedup at 256k context length and 2.37x end-to-end throughput improvement. Empirical validation on Ruler and Longbench confirms that FFD maintains model accuracy while delivering high-ratio sparsity.

Social Aspects · Alignment

Atticus Wang, Iván Arcuschin, Arthur Conmy

Large language model (LLM) post-training typically relies on a training signal from a reward model (RM), such as for reinforcement learning from human feedback. Previous work shows that this signal can be biased in attributes such as length, format, and sycophancy. In this work, we introduce and study the research problem of automatically finding reward model biases in natural language. We offer a simple approach of using an LLM to iteratively propose and refine candidate biases. Our method can recover known biases and surface novel ones: for example, we found that Skywork-V2-8B, a leading open-weight reward model, often mistakenly favors responses with redundant spacing and responses with hallucinated content. In addition, we show evidence that iteration provides benefits over flat best-of-N search. We hope our work contributes to further research on improving RMs through automated interpretability methods.

Social Aspects · Accountability, Transparency, and Interpretability

Iván Arcuschin, David Chanin, Adrià Garriga-Alonso, Oana-Maria Camburu

Large Language Models (LLMs) often provide chain-of-thought (CoT) reasoning traces that appear plausible, but may hide internal biases. We call these *unverbalized biases*. Monitoring models via their stated reasoning is therefore unreliable, and existing bias evaluations typically require predefined categories and hand-crafted datasets. In this work, we introduce a fully automated, black-box pipeline for detecting task-specific unverbalized biases. Given a task dataset, the pipeline uses LLM autoraters to generate candidate bias concepts. It then tests each concept on progressively larger input samples by generating positive and negative variations, and applies statistical techniques for multiple testing and early stopping. A concept is flagged as an unverbalized bias if it yields statistically significant performance differences while not being cited as justification in the model's CoTs. We evaluate our pipeline across six LLMs on three decision tasks (hiring, loan approval, and university admissions). Our technique automatically discovers previously unknown biases in these models (e.g., Spanish fluency, English proficiency, writing formality). In the same run, the pipeline also validates biases that were manually identified by prior work (gender, race, religion, ethnicity). More broadly, our proposed approach provides a practical, scalable path to automatic task-specific bias discovery.

Deep Learning · Large Language Models

Haonan Song, Qingchen Xie, Huan Zhu, Feng Xiao, Luxi Xing, Liu Kang, Fuzhen Li, Zhiyong Zheng, Feng Jiang, Ziheng Li 等

Generative Reward Models (GRMs) have demonstrated strong performance in reward modeling, due to their interpretability and potential for refinement through reinforcement learning (RL). However, widely used pairwise GRMs create a computational bottleneck in reinforcement learning from human feedback (RLHF), when calibrating or aggregating preference signals over $n$ candidates, often incurring $\mathcal{O}(n^2)$ pairwise judgments. To address this issue, we propose Intergroup Relative Preference Modeling (IRPM), an RL-based method that extends the Bradley--Terry preference-learning paradigm via intergroup comparisons to train \emph{pointwise} GRMs from pairwise preference data. IRPM derives pointwise reward for each response by contrasting groups of chosen vs.\ rejected samples, enabling pointwise scores comparable across candidate sets and $\mathcal{O}(n)$ reward evaluation for a variable number of candidates during RL training, while preserving interpretability and scalability. Experiments show that IRPM achieves state-of-the-art performance among pointwise GRMs on RM-Bench, JudgeBench and RewardBench, and approaches the performance of leading pairwise GRMs. In addition, IRPM achieves substantial gains in post-training evaluations, demonstrating its effectiveness.

Xiuyu Li, Jinkai Zhang, Mingyang Yi, Yu Li, Longqiang Wang, Yue Wang, Ju Fan

Reinforcement Learning (RL) post-training alignment for language models is effective, but also costly and unstable in practice, owing to its complicated training process. To address this, we propose a training-free inference method to sample directly from the optimal RL policy. The transition probability applied to Masked Language Modeling (MLM) consists of a reference policy model and an energy term. Based on this, our algorithm, Energy-Guided Test-Time Scaling (ETS), estimates the key energy term via online Monte Carlo, with a provable convergence rate. Moreover, to ensure practical efficiency, ETS leverages modern acceleration frameworks alongside tailored importance sampling estimators, substantially reducing inference latency while provably preserving sampling quality. Experiments on MLM (including autoregressive models and diffusion language models) across reasoning, coding, and science benchmarks show that our ETS consistently improves generation quality, validating its effectiveness and design.

General Machine Learning · Methodology

Yingbo HAO, Hanyong Shao, Ting Song, Yan Xia, Di Zhang, Shaohan Huang, Xun Wu, Songchen Xu, Le Xu, Li Dong 等

NVIDIA's 2:4 Sparse Tensor Cores deliver $2\times$ throughput but demand 50% pruning—a ratio that collapses LLM reasoning accuracy (Qwen3: 54%→15%). Milder $(2N-2):2N$ patterns (e.g., 6:8, 25% pruning) preserve accuracy yet receive *no* hardware support, falling back to dense execution. We present **SlideSparse**, the first system to unlock Sparse Tensor Core acceleration for the $(2N-2):2N$ model family on commodity GPUs. Our *Sliding Window Decomposition* losslessly rewrites any $(2N-2):2N$ block into $N-1$ overlapping 2:4-compliant windows; *activation lifting* fuses the corresponding activation rearrangement into per-token quantization at near-zero cost. Integrated into vLLM, **SlideSparse** is evaluated across five GPUs (A100, H100, B200, RTX 4090, RTX 5080), three precisions (INT8, FP8, BF16), and the Llama/Qwen/BitNet model families. On compute-bound workloads, speedup approaches the theoretical $N/(N-1)$ limit—Qwen2.5-7B with 6:8 sparsity achieves $1.33\times$, matching the bound exactly—establishing $(2N-2):2N$ as a practical path to accuracy-preserving LLM acceleration.

Deep Learning · Theory

Andreas Maurer, Erfan Mirzaei, Massimiliano Pontil

This paper provides data-dependent bounds on the expected error of the Gibbs algorithm in the overparameterized interpolation regime, where low training errors are also obtained for impossible data, such as random labels in classification. The results show that generalization in the low-temperature regime is already signaled by small training errors in the more classical high temperature regime. The bounds are stable under approximation with Langevin Monte Carlo algorithms. The analysis motivates the design of an algorithm to compute bounds, which on the MNIST and CIFAR-10 datasets yield nontrivial, close predictions on the test error for true labeled data, while maintaining a correct upper bound on the test error for random labels.

General Machine Learning · Causality

Arvind Raghavan

Previous work establishing completeness results for *counterfactual identification* has been limited to the setting where the input data belongs to observational and interventional distributions (Layers 1 and 2 of Pearl's Causal Hierarchy), since it was generally presumed impossible to obtain data from counterfactual distributions, belonging to Layer 3. However, recent work (Raghavan & Bareinboim, 2025) has formally characterized a family of counterfactual distributions which can be directly estimated via experimental methods - a notion they call *counterfactual realizabilty*. This leaves open the question of what *additional* Layer 3 quantities now become identifiable, given this new access to (some) Layer 3 data. We develop the **ctfIDu+** algorithm for identifying a counterfactual query from an arbitrary set of Layer 3 data, and prove that it is complete for this task. Using this, we establish the theoretical limit of which counterfactuals can be identified from physically realizable data, thus implying the *fundamental limit to exact causal inference in the non-parametric setting*. Finally, we derive novel analytic bounds for important non-identifiable quantities given realizable counterfactual data, that are provably tighter than the previously established benchmark. We corroborate using simulations that even if a quantity is non-identifiable, counterfactual data can be used to further tighten bounds for its range.