论文检索

Deep Learning · Generative Models and Autoencoders

Hao Xintong, Rui-Jie Zhu, Ge Zhang, Ke Shen, Chenggang Li

Despite the impressive capabilities of large language models across various tasks, their continued scaling is severely hampered not only by data scarcity but also by the performance degradation associated with excessive data repetition during training. To overcome this critical bottleneck, we introduce the Massive Genre-Audience (MGA) reformulation method, a framework designed to augment corpora in a way that supports more effective model performance scaling. Instead of relying on complex, predefined seed systems, MGA systematically reformulates existing corpora into diverse, contextually-rich variations by adaptively generating genre-audience pairs. We present this framework and the resulting 770 billion token MGACorpus, created as a practical instantiation of our methodology. We experimentally validate MGA's core benefits by demonstrating superior scaling properties, in terms of both model size and data budget, against data repetition and upsampling (up to 13B parameters). Furthermore, our comprehensive analysis investigates the role of synthesis principles in generation quality and reveals nuances in evaluating model capabilities using standard loss metrics. Our work shows that a systematic framework like MGA provides a reliable pathway to substantially augment training datasets, effectively alleviating repetition bottlenecks and enabling more efficient scaling of large language models.

Optimization · Non-Convex

Yuman Wu, Xiaochuan Gong, Jie Hao, Mingrui Liu

Bilevel optimization is a hierarchical framework where an upper-level optimization problem is constrained by a lower-level problem, commonly used in machine learning applications such as hyperparameter optimization. Existing bilevel optimization methods typically assume strong convexity or Polyak-Łojasiewicz (PL) conditions for the lower-level function to establish non-asymptotic convergence to a solution with a small hypergradient. However, these assumptions may not hold in practice, and recent work (Chen et al. 2024) has shown that bilevel optimization is inherently intractable for general convex lower-level functions with the goal of finding small hypergradients. In this paper, we identify a tractable class of bilevel optimization problems that interpolates between lower-level strong convexity and general convexity via lower-level uniform convexity. For uniformly convex lower-level functions with exponent $p\geq 2$, we establish a novel implicit differentiation theorem characterizing the hyperobjective's smoothness property. Building on this, we design a new stochastic algorithm, termed UniBiO, with provable convergence guarantees, based on an oracle that provides stochastic gradient and Hessian-vector product information for the bilevel problems. Our algorithm achieves $\widetilde{O}(\epsilon^{-5p+6})$ oracle complexity bound for finding $\epsilon$-stationary points. Notably, our complexity bounds match the optimal rates in terms of the $\epsilon$ dependency for strongly convex lower-level functions ($p=2$), up to logarithmic factors. Our theoretical findings are validated through experiments on synthetic tasks and data hyper-cleaning, demonstrating the effectiveness of our proposed algorithm.

Guhao Feng, Shengjie Luo, Kai Hua, Ge Zhang, Wenhao Huang, Di He, Tianle Cai

The static "train then deploy" paradigm fundamentally limits Large Language Models (LLMs) from dynamically adapting their weights in response to continuous streams of new information inherent in real-world tasks. Test-Time Training (TTT) offers a compelling alternative by updating a subset of model parameters (fast weights) at inference time, yet its potential in the current LLM ecosystem is hindered by critical barriers including architectural incompatibility, computational inefficiency and misaligned fast weight objectives for language modeling. In this work, we introduce **In-Place Test-Time Training (In-Place TTT)**, a framework that seamlessly endows LLMs with Test-Time Training ability. In-Place TTT treats the final projection matrix of the ubiquitous MLP blocks as its adaptable fast weights, enabling a ``drop-in" enhancement for LLMs without costly retraining from scratch. Furthermore, we replace TTT's generic reconstruction objective with a tailored, theoretically-grounded objective explicitly aligned with the Next-Token-Prediction task governing autoregressive language modeling. This principled objective, combined with an efficient chunk-wise update mechanism, results in a highly scalable algorithm compatible with context parallelism. Extensive experiments validate our framework's effectiveness: as an in-place enhancement, it enables a 4B-parameter model to achieve superior performance on tasks with contexts up to 128k, and when pretrained from scratch, it consistently outperforms competitive TTT-related approaches. Ablation study results further provide deeper insights on our design choices. Collectively, our results establish In-Place TTT as a promising step towards a paradigm of continual learning in LLMs.

Deep Learning · Everything Else

Haonan Wang, Chao Du, Kenji Kawaguchi, Tianyu Pang

Majority voting has proven effective for close-ended question answering by aggregating parallel reasoning traces. However, it is not directly applicable to open-ended reasoning, such as code generation and web-based deep research, where a “majority” over complete solutions is ill-defined. We introduce THINKMERGE, a training-free, plug-and-play decoding strategy that runs K parallel reasoning traces and averages their next-token logits at synchronization points to produce a single coherent output. THINKMERGE integrates seamlessly with vLLM/SGLang and remains compatible with standard decoding techniques such as Top-p/Top-k. Empirically, it matches or surpasses majority voting on AIME and GPQA, while delivering consistent gains on open-ended coding tasks: on LiveCodeBench (hard), pass@1 improves by +8.28% for DeepCoder-14B-Preview and +7.58% for Qwen3-8B. Beyond code, we further show that THINKMERGE improves web-based deep-research agents (e.g., WebSailor-7B/32B) across GAIA, BrowseComp-en/zh, and XbenchDeepSearch. These results demonstrate that parallel test-time scaling can benefit open-ended reasoning without relying on voting over complete outputs.

Theory · Probabilistic Methods

Yunrui Guan, Krishna Balasubramanian, Shiqian Ma

We study generative modeling on convex domains using flow matching and mirror maps, and identify two fundamental challenges. First, standard log-barrier mirror maps induce heavy-tailed dual distributions, leading to ill-posed dynamics. Second, coupling with Gaussian priors performs poorly when matching heavy-tailed targets. To address these issues, we propose Mirror Flow Matching based on a \emph{regularized mirror map} that controls dual tail behavior and guarantees finite moments, together with coupling to a Student-$t$ prior that aligns with heavy-tailed targets and stabilizes training. We provide theoretical guarantees, including spatial Lipschitzness and temporal regularity of the velocity field, Wasserstein convergence rates for flow matching with Student-$t$ priors and primal-space guarantees for constrained generation, under $\varepsilon$-accurate learned velocity fields. Empirically, our method outperforms baselines in synthetic convex-domain simulations and achieves competitive sample quality on real-world constrained generative tasks.

Deep Learning · Theory

Gabriel Mel

Local loss geometry in machine learning is inherently a two-operator concept. While a single loss is locally characterized by its Hessian spectrum, practical learning depends on both training and test losses, whose joint geometry is determined not only by their spectra but by the alignment of their eigenspaces. We establish general foundations for this two-loss geometry by deriving a universal local fluctuation law: the expected test-loss increment under small training perturbations is a trace combining train and test spectral data with a precise factor quantifying eigenvector overlap. We further prove a transfer law describing how overlaps transform under noise. As a solvable model, we apply these results to ridge regression under arbitrary covariate shift, where operator-valued free probability yields asymptotically exact overlap decompositions that identify overlaps as the natural quantities for specifying shift, and resolve multiple descent: error peaks are governed by eigenspace misalignment rather than Hessian ill-conditioning alone. We then validate the fluctuation law in multilayer perceptrons, develop scalable estimators for overlap functionals based on subspace iteration and kernel polynomial methods, and apply them to a ResNet-20 trained on CIFAR-10, showing that class imbalance reshapes train–test geometry through induced misalignment. Together, these results establish eigenvector overlaps as the fundamental missing ingredient in local loss geometry, providing both theoretical foundations and practical tools for analyzing generalization in modern neural networks.

Computer Vision · Image and Video Generation

Jiayi Lyu, Leigang Qu, Wenjing Zhang, Hanyu Jiang, Kai Liu, Zhenglin Zhou, Xiaobo Xia, Jian Xue, Tat-Seng Chua

Realistic talking-head video generation is critical for virtual avatars, film production, and interactive systems. Current methods struggle with nuanced emotional expressions due to the lack of fine-grained emotion control. To address this issue, we introduce a novel two-stage method (AUHead) to disentangle fine-grained emotion control, i.e. , Action Units (AUs), from audio and achieve controllable generation. In the first stage, we explore the AU generation abilities of large audio-language models (ALMs), by spatial-temporal AU tokenization and an "emotion-then-AU" chain-of-thought mechanism. It aims to disentangle AUs from raw speech, effectively capturing subtle emotional cues. In the second stage, we propose an AU-driven controllable diffusion model that synthesizes realistic talking-head videos conditioned on AU sequences. Specifically, we first map the AU sequences into the structured 2D facial representation to enhance spatial fidelity, and then model the AU-vision interaction within cross-attention modules. To achieve flexible AU-quality trade-off control, we introduce an AU disentanglement guidance strategy during inference, further refining the emotional expressiveness and identity consistency of the generated videos. Results on benchmark datasets demonstrate that our approach achieves competitive performance in emotional realism, accurate lip synchronization, and visual coherence, significantly surpassing existing techniques. Our implementation is available at https://github.com/laura990501/AUHead_ICLR

Social Aspects · Privacy-preserving Statistics and Machine Learning

Lorenzo Rossi, Bartłomiej Marek, Franziska Boenisch, Adam Dziedzic

Assessing the privacy of large language models (LLMs) presents significant challenges. In particular, most existing methods for auditing *differential privacy* require the insertion of specially crafted canary data *during training*, making them impractical for auditing already-trained models without costly retraining. Additionally, *dataset inference*, which audits whether a suspect dataset was used to train a model, is *infeasible* without access to a private non-member held-out dataset. Yet, such held-out datasets are often unavailable or difficult to construct for real-world cases since they have to be from the same distribution (IID) as the suspect data. These limitations severely hinder the ability to conduct scalable, *post-hoc* audits. To enable such audits, this work introduces **natural identifiers (NIDs)** as a novel solution to the above-mentioned challenges. NIDs are structured random strings, such as cryptographic hashes and shortened URLs, naturally occurring in common LLM training datasets. Their format enables the generation of unlimited additional random strings from the same distribution, which can act as alternative canaries for audits and as same-distribution held-out data for dataset inference. Our evaluation highlights that indeed, using NIDs, we can facilitate post-hoc differential privacy auditing *without any retraining* and enable dataset inference for any suspect dataset containing NIDs without the need for a private non-member held-out dataset.

Computer Vision · Vision Models & Multimodal

Linjie Li, Mahtab Bigverdi, Jiawei Gu, Zixian Ma, Yinuo Yang, Ziang Li, Yejin Choi, Ranjay Krishna

Spatial cognition is essential for human intelligence, enabling problem-solving through visual simulations rather than relying solely on verbal reasoning. However, existing AI benchmarks primarily assess verbal reasoning, neglecting the complexities of non-verbal, multi-step visual simulation. We introduce STARE (Spatial Transformations and Reasoning Evaluation), a benchmark designed to evaluate multimodal large language models on tasks better solved through multi-step visual simulation. STARE features ~4K tasks spanning foundational geometric transformations (2D and 3D), integrated spatial reasoning (cube net folding and tangram puzzles), and real-world spatial reasoning (perspective and temporal reasoning), reflecting practical cognitive challenges like object assembly, mechanical diagram interpretation, and everyday spatial navigation. Our evaluations show that models excel at reasoning over simpler 2D transformations, but perform close to random chance on more complex tasks like 3D cube net folding and tangram puzzles that require multi-step visual simulations. Humans achieve near-perfect accuracy but take considerable time (up to 28.0s) on complex tasks, reducing response time by 7.5 seconds on average with intermediate visual simulations. In contrast, models exhibit inconsistent performance gains from visual simulations, improving on most tasks but declining in specific cases like tangram puzzles (GPT-4o, o1) and cube net folding (Claude-3.5, Gemini-2.0 Flash), indicating that models cannot consistently leverage intermediate visual information. Even o3, a strong reasoning model, lags significantly behind human performance across tasks. By evaluating non-verbal visual reasoning beyond conventional text-based benchmarks, STARE highlights critical gaps in current AI spatial capabilities and sets a new standard for assessing spatial intelligence in multimodal models.

Computer Vision · 3D Rendering & Reconstruction

Wenzong Ma, Zhuoxiao Li, Jinjing Zhu, Tongyan Hua, Kanghao Chen, Zidong Cao, Da Yang, Peilun Shi, Yibo Zhou, Wufan Zhao 等

Recent advances in large-scale 3D scene reconstruction using unmanned aerial vehicles (UAVs) have spurred increasing interest in neural rendering techniques. However, existing approaches with conventional cameras struggle to capture consistent multi-view images of scenes, particularly in extremely blurred and low-light environments, due to the inherent limitations in dynamic range caused by long exposure and motion blur resulting from camera motion. As a promising solution, bio-inspired event cameras exhibit robustness in extreme scenarios, due to their high dynamic range and microsecond-level temporal resolution. Nevertheless, dedicated event datasets specifically tailored for large-scale UAV 3D scene reconstruction remain limited. To bridge this gap, we introduce SkyEvents, a pioneering large-scale event-enhanced UAV dataset for 3D scene reconstruction, incorporating RGB, event, and LiDAR data. SkyEvents encompasses 45 sequences, spanning over 8 hours of video, captured across a diverse set of illumination conditions, scenarios, and flight altitudes. To facilitate the event-based 3D scene reconstruction with SkyEvents, we propose the Geometry-constrained Timestamp Alignment (GTA) module to align timestamps between the event and RGB cameras. Furthermore, we introduce a Region-wise Event Rendering (RER) loss for supervising the rendering optimization. With SkyEvents, we aim to motivate and equip researchers to advance large-scale 3D scene reconstruction in challenging environments, harnessing the unique strengths of event cameras. Dataset and code will be available at https://github.com/Anthony-ECPKN/SkyEvent.

Computer Vision · Segmentation

Weijia Dou, Xu Zhang, Yi Bin, Jian Liu, Bo Peng, Guoqing Wang, Yang Yang, Heng Tao Shen

Recent attempts to transfer features from 2D Vision–Language Models (VLMs) to 3D semantic segmentation expose a persistent trade-off. Directly projecting 2D features into 3D yields noisy and fragmented predictions, whereas enforcing geometric coherence necessitates costly training pipelines and large-scale, annotated 3D data. We argue that this limitation stems from the dominant \textit{segmentation-and-matching} paradigm, which fails to reconcile 2D semantics with 3D geometric structure. The geometric cues are not eliminated during the 2D-to-3D transfer but remain latent within the noisy and view-aggregated features. To exploit this property, we propose \textbf{GeoPurify} that applies a small Student Affinity Network to purify 2D VLM-generated 3D point features using geometric priors distilled from a 3D self-supervised teacher model. During inference, we devise a Geometry-Guided Pooling module to further denoise the point cloud and ensure the semantic and structural consistency. Benefiting from latent geometric information and the learned affinity network, GeoPurify effectively mitigates the trade-off and achieves superior data efficiency. Extensive experiments on major 3D benchmarks demonstrate that GeoPurify achieves or surpasses state-of-the-art performance while utilizing only \textbf{$\sim$1.5\%} of the training data.

Computer Vision · Everything Else

Zhiwei Ning, Xuanang Gao, Jiaxi Cao, Runze Yang, Huiying Xu, Xinzhong Zhu, Jie Yang, Wei Liu

Linear modeling methods like Mamba have been merged as the effective backbone for the 3D object detection task. However, previous Mamba-based methods utilize the bidirectional encoding for the whole non-empty voxel sequence, which contains abundant useless background information in the scenes. Though directly encoding foreground voxels appears to be a plausible solution, it tends to degrade detection performance. We attribute this to the response attenuation and restricted context representation in the linear modeling for fore-only sequences. To address this problem, we propose a novel backbone, termed Fore-Mamba3D, to focus on the foreground enhancement by modifying Mamba-based encoder. The foreground voxels are first sampled according to the predicted scores. Considering the response attenuation existing in the interaction of foreground voxels across different instances, we design a regional-to-global slide window (RGSW) to propagate the information from regional split to the entire sequence. Furthermore, a semantic-assisted and state spatial fusion module (SASFMamba) is proposed to enrich contextual representation by enhancing semantic and geometric awareness within the Mamba model. Our method emphasizes foreground-only encoding and alleviates the distance-based and causal dependencies in the linear autoregression model. The superior performance across various benchmarks demonstrates the effectiveness of Fore-Mamba3D in the 3D object detection task.

Reinforcement Learning · Inverse

Filippo Lazzati, Alberto Maria Metelli

In Reward Learning (ReL), we are given feedback on an unknown target reward, and the goal is to use this information to recover it in order to carry out some downstream application, e.g., planning. When the feedback is not informative enough, the target reward is only partially identifiable, i.e., there exists a set of rewards, called the feasible set, that are equally plausible candidates for the target reward. In these cases, the ReL algorithm might recover a reward function different from the target reward, possibly leading to a failure in the application. In this paper, we introduce a general ReL framework that permits to quantify the drop in "performance" suffered in the considered application because of identifiability issues. Building on this, we propose a robust approach to address the identifiability problem in a principled way, by maximizing the "performance" with respect to the worst-case reward in the feasible set. We then develop Rob-ReL, a ReL algorithm that applies this robust approach to the subset of ReL problems aimed at assessing a preference between two policies, and we provide theoretical guarantees on sample and iteration complexity for Rob-ReL. We conclude with some numerical simulations to illustrate the setting and empirically characterize Rob-ReL.

General Machine Learning · Representation Learning

Fengyu Cai, Tong Chen, Xinran Zhao, Sihao Chen, Hongming Zhang, Sherry Wu, Iryna Gurevych, Heinz Koeppl

Dense retrievers play a vital role in accessing external and specialized knowledge to augment language models (LMs). Training dense retrievers typically requires annotated query-document pairs, which are costly to create and scarce in specialized domains (e.g., code) or in complex settings (e.g., requiring reasoning). These practical challenges have sparked growing interest in self-supervised retriever learning. Since LMs are trained to capture token-level dependencies through a self-supervised learning objective (i.e., next token prediction), we can analogously cast retrieval as learning dependencies among chunks of tokens. This analogy naturally leads to the question: How can we adapt self‑supervised learning objectives in the spirit of language modeling to train retrievers? To answer this question, we introduce Revela, a unified and scalable training framework for self-supervised retriever learning via language modeling. Revela models semantic dependencies among documents by conditioning next token prediction on local and cross-document context through an in-batch attention mechanism. This attention is weighted by retriever-computed similarity scores, enabling the retriever to be optimized as part of language modeling. We evaluate Revela on domain-specific (CoIR), reasoning-intensive (BRIGHT), and general-domain (BEIR) benchmarks across various retriever backbones. Without annotated or synthetic query-document pairs, Revela surpasses larger supervised models and proprietary APIs on both CoIR and BRIGHT. It achieves BEIR's unsupervised SoTA with ~1000x less training data and 10x less compute. Performance increases with batch size and model size, highlighting Revela's scalability and its promise for self‑supervised retriever learning.

Applications · Chemistry and Drug Discovery

Luke Thompson, Davy Guan, Slade Matthews, Dai Shi, Junbin Gao, Andi Han

Molecular dynamics (MD) simulations underpin modern computational drug discovery, materials science, and biochemistry. Recent machine learning models provide high-fidelity MD predictions without the need for repeated quantum-mechanical force calculations, enabling significant speedups over conventional pipelines. Yet many such methods typically enforce strict equivariance and rely on sequential rollouts, thus limiting their flexibility and simulation efficiency. They are also commonly single-task, trained on individual molecules and fixed time frames, which restricts generalization to unseen compounds and extended timesteps. To address these issues, we propose Atomistic Transformer Operator for Molecules (ATOM), a pretrained transformer neural operator for multi-task molecular dynamics. ATOM adopts a quasi-equivariant design that does not require an explicit molecular graph and employs a temporal attention mechanism to enable accurate, parallel decoding of multiple future states. To support operator pretraining across chemicals and timescales, we curate TG80, a large, diverse, and numerically stable MD dataset with over 2.5 million femtoseconds of trajectories across 80 compounds. ATOM achieves state-of-the-art performance on established single-task benchmarks, such as MD17, RMD17, and MD22. After multi-task pretraining on TG80, ATOM shows exceptional zero-shot and robust generalization to unseen molecules across varying time horizons. We believe ATOM represents a significant step toward accurate, efficient, and transferable molecular dynamics models.

Applications · Physics

Tianrun Gao, Haoren Zheng, Wenhao Deng, Haodong Feng, Tao Zhang, Ruiqi Feng, Qianyi Chen, Tailin Wu

Real-world physical systems are inherently complex, often involving the coupling of multiple physics, making their simulation both highly valuable and challenging. Many mainstream approaches face challenges when dealing with decoupled data. Besides, they also suffer from low efficiency and fidelity in strongly coupled spatio-temporal physical systems. Here we propose GenCP, a novel and elegant generative paradigm for coupled multiphysics simulation. By formulating coupled-physics modeling as a probability modeling problem, our key innovation is to integrate probability density evolution in generative modeling with iterative multiphysics coupling, thereby enabling training on data from decoupled simulation and inferring coupled physics during sampling. We also utilize operator-splitting theory in the space of probability evolution to establish error controllability guarantees for this “conditional-to-joint” sampling scheme. We evaluate our paradigm on a synthetic setting and three challenging multiphysics scenarios to demonstrate both principled insight and superior application performance of GenCP. Code is available at this repo: https://github.com/AI4Science-WestlakeU/GenCP.

Computer Vision · Image and Video Generation

Xianghong Fang, Yuan Yuan, Dehan Kong, Tim G. J. Rudner

Vector Quantization (VQ) underpins modern discrete visual tokenization. However, training quantization modules for state-of-the-art VQ-based models requires significant computational resources which, in practice, all but prevents the development of novel, cutting-edge VQ techniques under resource constraints. To address this limitation, we propose VQ-Transplant, a simple framework that enables plug-and-play integration of new VQ modules into frozen, pre-trained tokenizers by replacing their native VQ modules. Crucially, the proposed transplantation process preserves all encoder-decoder parameters, obviating the need for costly end-to-end retraining when modifying the quantization method. To mitigate decoder-quantization mismatch, we introduce a lightweight decoder adaptation strategy (trained for only 5 epochs on ImageNet-1k) to align feature priors with the new quantization space. In our empirical evaluation, we find that VQ-Transplant allows obtaining near state-of-the-art reconstruction fidelity for industry-level models like VAR while reducing the training cost by 95%. VQ-Transplant democratizes quantization research by enabling resource-efficient integration of novel VQ techniques while matching industry-level reconstruction performance.

Reinforcement Learning · Deep RL

Yuhang Li, Reena Elangovan, Xin Dong, Priyadarshini Panda, Brucek Khailany

Reinforcement learning with verifiable rewards (RLVR) has become a trending paradigm for training reasoning large language models (LLMs). However, due to the autoregressive decoding nature of LLMs, the rollout process becomes the efficiency bottleneck of RL training, consisting of up to 70\% of the total training time. In this work, we propose Quantized Reinforcement Learning (QuRL) that uses a quantized actor for accelerating the rollout. We address two challenges in QuRL. First, we propose Adaptive Clipping Range (ACR) that dynamically adjusts the clipping ratio based on the policy ratio between the full-precision actor and the quantized actor, which is essential for mitigating long-term training collapse. Second, we identify the weight update problem, where weight changes between RL steps are extremely small, making it difficult for the quantization operation to capture them effectively. We mitigate this problem through the invariant scaling technique that reduces quantization noise and increases weight update. We evaluate our method with INT8 and FP8 quantization experiments on DeepScaleR and DAPO, and achieve 20% to 80% faster rollout during training.

Deep Learning · Graph Neural Networks

Fangbing Liu, Qing Wang

Spectral Graph Neural Networks (GNNs) achieve strong performance in node classification, yet their node distinguishability remains poorly understood. We analyze how graph matrices and node features jointly influence node distinguishability. Further, we derive a theoretical lower bound on the number of distinguishable nodes, which is governed by two key factors: distinct eigenvalues in the graph matrix and nonzero frequency components of node features in the eigenbasis. Based on these insights, we propose AdaSpec, an adaptive graph matrix generation module that enhances node distinguishability of spectral GNNs without increasing the order of computational complexity. We prove that AdaSpec preserves permutation equivariance, ensuring that reordering the graph nodes results in a corresponding reordering of the node embeddings. Experiments across eighteen benchmark datasets validate AdaSpec's effectiveness in improving node distinguishability of spectral GNNs.

Social Aspects · Accountability, Transparency and Interpretability

Guan Zhe Hong, Bhavya Vasudeva, Vatsal Sharan, Cyrus Rashtchian, Prabhakar Raghavan, Rina Panigrahy

When large language models (LLMs) use in-context learning (ICL) to solve a new task, they must infer latent concepts from demonstration examples. This raises the question of whether and how transformers represent latent structures as part of their computation. Our work experiments with several controlled tasks, studying this question using mechanistic interpretability. First, we show that in transitive reasoning tasks with a latent, discrete concept, the model successfully identifies the latent concept and does step-by-step concept composition. This builds upon prior work that analyzes single-step reasoning. Then, we consider tasks parameterized by a latent numerical concept. We discover low-dimensional subspaces in the model's representation space, where the geometry cleanly reflects the underlying parameterization. Overall, we show that small and large models can indeed disentangle and utilize latent concepts that they learn in-context from a handful of abbreviated demonstrations.