ICLR 2026 论文列表

Object referring aims to detect all objects in an image that match a given natural language description. We argue that a robust object referring model should be grounded, meaning its predictions should be both explainable and faithful to the visual content. Specifically, it should satisfy two key properties: 1) Verifiable, by producing interpretable reasoning that justifies its predictions and clearly links them to visual evidence; and 2) Trustworthy, by learning to abstain when no object in the image satisfies the given expression. However, most methods treat referring as a direct bounding box prediction task, offering limited interpretability and struggling to reject expressions with no matching object. In this work, we propose Rex-Thinker, a model that formulates object referring as an explicit CoT reasoning task. Given a referring expression, we first identify all candidate object instances corresponding to the referred object category. Rex-Thinker then performs step-by-step reasoning over each candidate to assess whether it matches the given expression, before making a final prediction. To support this paradigm, we construct a large-scale CoT-style referring dataset named HumanRef-CoT by prompting GPT-4o on the HumanRef dataset. Each reasoning trace follows a structured planning, action, and summarization format, enabling the model to learn decomposed, interpretable reasoning over object candidates. We then train Rex-Thinker in two stages: a cold-start supervised fine-tuning phase to teach the model how to perform structured reasoning, followed by GRPO-based RL learning to improve accuracy and generalization. Experiments show that our approach outperforms standard baselines in both precision and interpretability on in-domain evaluation, while also demonstrating improved ability to reject hallucinated outputs and strong generalization in out-of-domain settings.

Machine unlearning (MU) for large language models (LLMs), commonly referred to as LLM unlearning, seeks to remove specific undesirable data or knowledge from a trained model, while maintaining its performance on standard tasks. While unlearning plays a vital role in protecting data privacy, enforcing copyright, and mitigating sociotechnical harms in LLMs, we identify a new vulnerability post-unlearning: unlearning trace detection. We discover that unlearning leaves behind persistent "fingerprints" in LLMs, detectable traces in both model behavior and internal representations. These traces can be identified from output responses, even when prompted with forget-irrelevant inputs. Specifically, even a simple supervised classifier can determine whether a model has undergone unlearning, using only its prediction logits or even its textual outputs. Further analysis shows that these traces are embedded in intermediate activations and propagate nonlinearly to the final layer, forming low-dimensional, learnable manifolds in activation space. Through extensive experiments, we demonstrate that unlearning traces can be detected with over 90% accuracy even under forget-irrelevant inputs, and that larger LLMs exhibit stronger detectability. These findings reveal that unlearning leaves measurable signatures, introducing a new risk of reverse-engineering forgotten information when a model is identified as unlearned, given an input query.

As the parameter size of large language models (LLMs) continues to grow, the latency of autoregressive inference increases due to memory-bound computational inefficiency. To address this, speculative decoding has been proposed, where a large target model verifies multiple tokens generated in parallel by a smaller draft model. However, the performance of speculative decoding is fundamentally limited by the draft model’s capacity, which stems from the parameter gap between the two models. To overcome this limitation, we propose RepSpec, which combines structural re-parameterization with draft model training. During training, redundant linear structures are introduced and later merged into the backbone network during inference, thus enhancing the draft model’s training effectiveness without increasing inference cost. By applying our method to improve the current state-of-the-art approach, EAGLE, we achieve a significant improvement in accepted sequence length. Furthermore, considering the specific characteristics of the speculative decoding scenario, we explore a hybrid training strategy that combines linear and nonlinear structures, which yields a further improvement in acceptance length.

Scaling laws play a central role in the success of Large Language Models (LLMs), enabling the prediction of model performance relative to compute budgets prior to training. While Transformers have been the dominant architecture, recent alternatives such as xLSTM offer linear complexity with respect to context length while remaining competitive in the billion-parameter regime. We conduct a comparative investigation on the scaling behavior of Transformers and xLSTM along the following lines, providing insights to guide future model design and deployment. First, we study the scaling behavior for xLSTM in compute-optimal and over-training regimes using both IsoFLOP and parametric fit approaches on a wide range of model sizes (80M-7B) and number of training tokens (2B-2T). Second, we examine the dependence of optimal model sizes on context length, a pivotal aspect that was largely ignored in previous work. Finally, we analyze inference-time scaling characteristics. Our findings reveal that in typical LLM training and inference scenarios, xLSTM scales favorably compared to Transformers. Notably, xLSTM models consistently Pareto-dominate Transformer models, delivering lower cross-entropy loss for the same compute budget.

Real world data often exhibits unknown, instance-specific symmetries that rarely exactly match a transformation group $G$ fixed a priori. Class-pose decompositions aim to create disentangled representations by factoring inputs into invariant features and a pose $g\in G$ defined relative to a training-dependent, \emph{arbitrary} canonical representation. We introduce \textsc{recon}, a class-pose agnostic \emph{canonical orientation normalization} that corrects arbitrary canonicals via a simple right-multiplication, yielding \emph{natural}, data-aligned canonicalizations. This enables (i) unsupervised discovery of instance-specific pose distributions, (ii) detection of out-of-distribution poses and (iii) a plug-and-play \emph{test-time canonicalization layer}. This layer can be attached on top of any pre-trained model to infuse group invariance, improving its performance without retraining. We demonstrate results on 2D image benchmarks and extend unsupervised instance-level pose discovery to 3D groups.

Transformers have demonstrated remarkable in-context learning abilities, adapting to new tasks from just a few examples without parameter updates. However, theoretical understanding of this phenomenon typically assumes fixed dependency structures, while real-world sequences exhibit flexible, context-dependent relationships. We address this gap by investigating whether transformers can learn causal structures -- the underlying dependencies between sequence elements -- directly from in-context examples. We propose a novel framework using Markov chains with randomly sampled causal dependencies, where transformers must infer which tokens depend on which predecessors to make accurate predictions. Our key contributions are threefold: (1) We prove that a two-layer transformer with relative position embeddings can implement Bayesian Model Averaging (BMA), the optimal statistical algorithm for causal structure inference; (2) Through extensive experiments and parameter-level analysis, we demonstrate that transformers trained on this task learn to approximate BMA, with attention patterns directly reflecting the inferred causal structures; (3) We provide information-theoretic guarantees showing how transformers recover causal dependencies and extend our analysis to continuous dynamical systems, revealing fundamental differences in representational requirements. Our findings bridge the gap between empirical observations of in-context learning and theoretical understanding, showing that transformers can perform sophisticated statistical inference over structural uncertainty.

With the advent of the neural network era, traditional machine learning methods have increasingly been overshadowed. Nevertheless, continuing to research about the role of geometry for learning in data science is crucial to envision and understand new principles behind the design of efficient machine learning. Linear classifiers are favored in certain tasks due to their reduced susceptibility to overfitting and their ability to provide interpretable decision boundaries. However, achieving both scalability and high predictive performance in linear classification remains a persistent challenge. Here, we propose a theoretical framework named geometric discriminant analysis (GDA). GDA includes the family of linear classifiers that can be expressed as function of a centroid discriminant basis (CDB0) - the connection line between two centroids - adjusted by geometric corrections under different constraints. We demonstrate that linear discriminant analysis (LDA) is a subcase of the GDA theoretical framework, and we show its convergence to CDB0 under certain conditions. Then, based on the GDA framework, we propose an efficient linear classifier named centroid discriminant analysis (CDA) which is defined as a special case of GDA under a 2D plane geometric constraint. CDA training is initialized starting from CDB0 and involves the iterative calculation of new adjusted centroid discriminant lines whose optimal rotations on the associated 2D planes are searched via Bayesian optimization. CDA has good scalability (quadratic time complexity) which is lower than LDA and support vectors machine (SVM) (cubic complexity). Results on 27 real datasets across classification tasks of standard images, medical images and chemical properties, offer empirical evidence that CDA outperforms other linear methods such as LDA, SVM and logistic regression (LR) in terms of scalability, performance and stability. Furthermore, we show that linear CDA can be generalized to nonlinear CDA via kernel method, demonstrating improvements on both linear CDA and kernel SVM with tests on three challenging datasets of images and chemical data. GDA general validity as a new theoretical framework may inspire the design of new classifiers under the definition of different geometric constraints, paving the way towards more deeper understanding of the role of geometry in learning from data.

Representation learning for register transfer level (RTL) circuits is fundamental to enabling accurate performance, power, and area (PPA) prediction, efficient circuit generation, and retrieval in automated chip design. Unlike general programming languages, RTL is inherently a structured dataflow graph where semantics are intrinsically bound to the topology from a hardware view. However, existing language-model-based approaches ignore the nature of RTL circuits and fail to capture topology-sensitive properties, leading to incomplete representation and limited performance for diverse downstream tasks. To address this, we introduce TopoRTL, a novel framework that explicitly learns topological differences across RTL circuits and preserves the behavior information. First, we decompose RTL designs into register cones and construct dual modalities initialized with behavior-aware tokenizers. Second, we design three topology-aware positional encodings and leverage attention mechanisms to enable the model to distinguish topological variations among register cones and RTL designs. Finally, we introduce a topology-guided cross-modal alignment strategy, employing contrastive learning over interleaved modality pairs under topological constraints to enforce semantic consistency and achieve superior modality alignment. Experiments demonstrate that explicit topological modeling is critical to improving RTL representation quality, and TopoRTL significantly outperforms existing methods across multiple downstream tasks.

Tool planning with large language models (LLMs), referring to selecting, organizing, and preparing the tools necessary to complete a user request, bridges the gap between natural language understanding and task execution. However, current works treat different tools as isolated components and fail to leverage the inherent dependencies of tools, leading to invalid planning results. Since tool dependencies are often incomplete, it becomes challenging for LLMs to accurately identify the appropriate tools required by a user request, especially when confronted with a large toolset. To solve this challenge, we propose GTool, which is the first work aiming to enhance the tool planning ability of LLMs under incomplete dependencies. GTool constructs a request-specific tool graph to select tools efficiently and generate the \<graph token\> which provides sufficient dependency information understandable by LLMs. Moreover, a missing dependency prediction task is designed to improve the reliability of GTool with incomplete dependencies. Without trimming LLMs, GTool can be seamlessly integrated with various LLM backbones without extensive retraining. Extensive experiments show that GTool achieves more than 29.6% performance improvements compared with the state-of-the-art (SOTA) baselines with a light-weight (7B) LLM backbone.

Aligning large language models (LLMs) is a central objective of post-training, often achieved through reward modeling and reinforcement learning methods. Among these, direct preference optimization (DPO) has emerged as a widely adopted technique that fine-tunes LLMs on preferred completions over less favorable ones. While most frontier LLMs do not disclose their curated preference pairs, the broader LLM community has released several open-source DPO datasets, including TuluDPO, ORPO, UltraFeedback, HelpSteer, and Code-Preference-Pairs. However, systematic comparisons remain scarce, largely due to the high computational cost and the lack of rich quality annotations, making it difficult to understand how preferences were selected, which task types they span, and how well they reflect human judgment on a per-sample level. In this work, we present the first comprehensive, data-centric analysis of popular open-source DPO corpora. We leverage the Magpie framework to annotate each sample for task category, input quality, and preference reward, a reward-model-based signal that validates the preference order without relying on human annotations. This enables a scalable, fine-grained inspection of preference quality across datasets, revealing structural and qualitative discrepancies in reward margins. Building on these insights, we systematically curate a new DPO mixture, **UltraMix**, that draws selectively from all five corpora while removing noisy or redundant samples. UltraMix is 30\% smaller than the best-performing individual dataset yet exceeds its performance across key benchmarks. We publicly release all annotations, metadata, and our curated mixture to facilitate future research in data-centric preference optimization.

Accurate tumor analysis is central to clinical radiology and precision oncology, where early detection, reliable lesion characterization, and pathology-level risk assessment directly guide diagnosis, staging, and treatment planning. Chain-of-Thought (CoT) reasoning is particularly critical in this setting, as it enables stepwise interpretation from imaging findings to clinical impressions and pathology-level conclusions, ensuring traceability and reducing diagnostic errors. Here, we target the clinical tumor analysis task and build a large-scale benchmark that operationalizes a multimodal reasoning pipeline, spanning findings, impressions, and pathology predictions. We curate TumorCoT, a large-scale dataset of 1.5M CoT-labeled VQA instructions paired with 3D CT scans, with step-aligned rationales and cross-modal alignments along the “findings → impression → pathology” trajectory, enabling standardized evaluation of both final accuracy and reasoning consistency. We further propose TumorChain, a multimodal interleaved reasoning framework that tightly couples 3D imaging encoders, clinical text understanding, and organ-level vision-language alignment. Through cross-modal alignment and iterative interleaved causal reasoning, TumorChain grounds visual evidence, aggregates conclusions, and issues pathology predictions after multiple rounds of self-refinement, improving traceability and reducing hallucination risk. TumorChain demonstrates consistent gains over strong unimodal and pipeline baselines in lesion detection, impression quality, and pathology classification, and successfully generalizes to the public DeepTumorVQA benchmark. Ablations validate the key contributions of interleaved reasoning and clinical CoT. Clinically, these advances lay the groundwork for reliable, interpretable tumor assessment to support real-world decision-making. We release the task, benchmark, and evaluation protocol to advance safe, explainable, and reproducible multimodal reasoning for high-stakes tumor analysis. Our project is available at https://anonymous.4open.science/r/TumorChain-D6E6.

Real-world robotic agents must act under partial observability and long horizons, where key cues may appear long before they affect decision making. However, most modern approaches rely solely on instantaneous information, without incorporating insights from the past. Standard recurrent or transformer models struggle with retaining and leveraging long-term dependencies: context windows truncate history, while naive memory extensions fail under scale and sparsity. We propose $\textbf{ELMUR}$ ($\textbf{E}$xternal $\textbf{L}$ayer $\textbf{M}$emory with $\textbf{U}$pdate/$\textbf{R}$ewrite), a transformer architecture with structured external memory. Each layer maintains memory embeddings, interacts with them via bidirectional cross-attention, and updates them through an $\textbf{L}$east $\textbf{R}$ecently $\textbf{U}$sed $\textbf{(LRU)}$ memory module using replacement or convex blending. ELMUR extends effective horizons up to 100,000 times beyond the attention window and achieves a 100% success rate on a synthetic T-Maze task with corridors up to one million steps. In POPGym, it outperforms baselines on more than half of the tasks. On MIKASA-Robo sparse-reward manipulation tasks with visual observations, it nearly doubles the performance of strong baselines. These results demonstrate that structured, layer-local external memory offers a simple and scalable approach to decision making under partial observability.

Full-waveform inversion (FWI) estimates physical parameters in the wave equation from limited measurements and has been widely applied in geophysical exploration, medical imaging, and non-destructive testing. Conventional FWI methods are limited by their notorious sensitivity to the accuracy of the initial models. Recent progress in continuous representation FWI (CR-FWI) demonstrates that representing parameter models with a coordinate-based neural network, such as implicit neural representation (INR), can mitigate the dependence on initial models. However, its underlying mechanism remains unclear, and INR-based FWI shows slower high-frequency convergence. In this work, we investigate the general CR-FWI framework and develop a unified theoretical understanding by extending the neural tangent kernel (NTK) for FWI to establish a wave-based NTK framework. Unlike standard NTK, our analysis reveals that wave-based NTK is not constant, both at initialization and during training, due to the inherent nonlinearity of FWI. We further show that the eigenvalue decay behavior of the wave-based NTK can explain why CR-FWI alleviates the dependency on initial models and shows slower high-frequency convergence. Building on these insights, we propose several CR-FWI methods with tailored eigenvalue decay properties for FWI, including a novel hybrid representation combining INR and multi-resolution grid (termed IG-FWI) that achieves a more balanced trade-off between robustness and high-frequency convergence rate. Applications in geophysical exploration on Marmousi, 2D SEG/EAGE Salt and Overthrust, 2004 BP model, and the more realistic 2014 Chevron models show the superior performance of our proposed methods compared to conventional FWI and existing INR-based FWI methods.

This paper presents *the first study of grokking in practical LLM pretraining*. Specifically, we investigate when an LLM memorizes the training data, when its generalization on downstream tasks starts to improve, and what happens if there is a lag between the two. Unlike existing works studying when a small model generalizes to limited and specified tasks during thousands epochs' training on algorithmic data, we focus on a practical setting for LLMs, i.e., near single-pass pretraining of next-token prediction on a cross-domain, large-scale corpus, and generalization on diverse benchmark tasks covering math/commonsense reasoning, code generation, and domain-specific retrieval. Our study, *for the first time, verifies that grokking still emerges in pretraining mixture-of-experts (MoE) LLMs*, though different local data groups may enter their grokking stages asynchronously due to the heterogeneity of their distributions and attributions to others. To find a mechanistic interpretation of this local grokking, we investigate the dynamics of training data's pathways (i.e., expert choices across layers in MoE). Our primary discovery is that *the pathways evolve from random, non-smooth across layers, instance-specific to more structured and transferable across samples*, despite the converged pretraining loss. This depicts a transition from memorization to generalization. Two novel metrics are developed to quantify these patterns: one computes the pathway similarity between samples, while the other measures the consistency of aggregated experts between subsequent layers for each sample. These training data based metrics induce near zero cost but can faithfully track and monitor the generalization of LLMs on downstream tasks, reducing reliance on costly instruction tuning and benchmark evaluations. We also ground our findings in a theoretical analysis of one-layer MoE, showing that more structured pathways improve the generalization bound.

Advances in diffusion, autoregressive, and hybrid models have enabled high-quality image synthesis for tasks such as text-to-image, editing, and reference-guided composition. Yet, existing benchmarks remain limited, either focus on isolated tasks, cover only narrow domains, or provide opaque scores without explaining failure modes. We introduce \textbf{ImagenWorld}, a benchmark of 3.6K condition sets spanning six core tasks (generation and editing, with single or multiple references) and six topical domains (artworks, photorealistic images, information graphics, textual graphics, computer graphics, and screenshots). The benchmark is supported by 20K fine-grained human annotations and an explainable evaluation schema that tags localized object-level and segment-level errors, complementing automated VLM-based metrics. Our large-scale evaluation of 14 models yields several insights: (1) models typically struggle more in editing tasks than in generation tasks, especially in local edits. (2) models excel in artistic and photorealistic settings but struggle with symbolic and text-heavy domains such as screenshots and information graphics. (3) closed-source systems lead overall, while targeted data curation (e.g., Qwen-Image) narrows the gap in text-heavy cases. (4) modern VLM-based metrics achieve Kendall accuracies up to 0.79, approximating human ranking, but fall short of fine-grained, explainable error attribution. ImagenWorld provides both a rigorous benchmark and a diagnostic tool to advance robust image generation.

Recent advances in multimodal learning have achieved remarkable success across diverse vision–language tasks. However, such progress heavily relies on large-scale image–text datasets, making training costly and inefficient. Prior efforts in dataset filtering and pruning attempt to mitigate this issue, but still require relatively large subsets to maintain performance and fail under very small subsets. Dataset distillation offers a promising alternative, yet existing multimodal dataset distillation methods require full-dataset training and joint optimization of image pixels and text features, making them architecture-dependent and limiting cross-architecture generalization. To overcome this, we propose a learning-free dataset distillation framework that eliminates the need for large-scale training and optimization while enhancing generalization across architectures. Our method uses CLIP to extract aligned image–text embeddings, obtains prototypes, and employs an unCLIP decoder to synthesize images, enabling efficient and scalable multimodal dataset distillation. Extensive experiments demonstrate that our approach consistently outperforms optimization-based dataset distillation and subset selection methods, achieving state-of-the-art cross-architecture generalization.

We introduce SCUBA, a benchmark designed to evaluate computer-use agents on customer relationship management (CRM) workflows within the Salesforce platform. SCUBA contains 300 task instances derived from real user interviews, spanning three primary personas—platform administrators, sales representatives, and service agents. The tasks test a range of enterprise-critical abilities, including Enterprise Software UI navigation, data manipulation, workflow automation, information retrieval, and troubleshooting. To ensure realism, SCUBA operates in Salesforce sandbox environments with support for parallel execution and fine-grained evaluation metrics to capture milestone progress. We benchmark a diverse set of agents under both zero-shot and demonstration-augmented settings. We observed huge performance gaps in different agent design paradigm and gaps between the open-source model and the closed-source model. In the zero-shot setting, open-source model powered computer-use agents that have strong performance on related benchmarks like OSWorld only have less than 5\% success rate on SCUBA, while methods built on closed-source models can still have up to 39\% percent task success rate. In the demonstration-augmented settings, task success rates can be improved to 50\% while simultaneously reducing time and costs by 13\% and 16\%, respectively. These findings highlight both the challenges of enterprise tasks automation and the promise of agentic solutions. By offering a realistic benchmark with interpretable evaluation, SCUBA aims to accelerate progress in building reliable computer-use agents for complex business software ecosystems.

Across many domains of science, stochastic models are an essential tool to understand the mechanisms underlying empirically observed data. Models can be of different levels of detail and accuracy, with models of high-fidelity (i.e., high accuracy) to the phenomena under study being often preferable. However, inferring parameters of high-fidelity models via simulation-based inference is challenging, especially when the simulator is computationally expensive. We introduce MF-(TS)NPE, a multifidelity approach to neural posterior estimation that uses transfer learning to leverage inexpensive low-fidelity simulations to efficiently infer parameters of high-fidelity simulators. MF-(TS)NPE applies the multifidelity scheme to both amortized and non-amortized neural posterior estimation. We further improve simulation efficiency by introducing A-MF-TSNPE, a sequential variant that uses an acquisition function targeting the predictive uncertainty of the density estimator to adaptively select high-fidelity parameters. On established benchmark and neuroscience tasks, our approaches require up to two orders of magnitude fewer high-fidelity simulations than current methods, while showing comparable performance. Overall, our approaches open new opportunities to perform efficient Bayesian inference on computationally expensive simulators.

Multimodal Large Language Models (MLLMs) hold promise for accelerating scientific discovery by interpreting complex experimental procedures. However, their true capabilities are poorly understood, as existing benchmarks neglect the fine-grained and long-horizon nature of authentic laboratory work, especially in wet-lab settings. To bridge this gap, we introduce ExpVid, the first benchmark designed to systematically evaluate MLLMs on scientific experiment videos. Curated from peer-reviewed video publications, ExpVid features a new three-level task hierarchy that mirrors the scientific process: (1) Fine-grained Perception of tools, materials, and actions; (2) Procedural Understanding of step order and completeness; and (3) Scientific Reasoning that connects the full experiment to its published conclusions. Our vision-centric annotation pipeline, combining automated generation with multi-disciplinary expert validation, ensures that tasks require visual grounding. We evaluate 19 leading MLLMs on ExpVid and find that while they excel at coarse-grained recognition, they struggle with disambiguating fine details, tracking state changes over time, and linking experimental procedures to scientific outcomes. Our results reveal a notable performance gap between proprietary and open-source models, particularly in high-order reasoning. ExpVid not only provides a diagnostic tool but also charts a roadmap for developing MLLMs capable of becoming trustworthy partners in scientific experimentation.