ICLR 2026 Papers

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.

Instruction tuning improves the LLMs performance but depends on high-quality training data. Recently, LLMs have been used to synthesize data, enhancing training with seeds like question-answer (QA) pairs. However, this synthesis often results in instruction examples similar to the seeds, lacking diversity and biasing real applications. Thus, we propose to extract instruction tuning data from web corpus with much rich knowledge. The most straightforward strategy is to quickly retrieve domain specific documents from the corpus and then extract all QA pairs of these documents for tuning LLMs, which has two main limitations. (1) Extracting all QA pairs using LLMs is prohibitively expensive; and (2) These extracted pairs are not all beneficial for the downstream applications, and incorporating all of them for tuning may even hurt the model performance. To overcome the limitations, we introduce $\texttt{EQUAL}$, an $\textbf{E}$ffective and scalable data extraction framework that iteratively interleaves document selection and extract high-$\textbf{QUAL}$ity QA pairs to optimize instruction tuning. $\texttt{EQUAL}$ first clusters the document set based on the embeddings generated by contrastive learning. Then it leverages the multi-armed bandit based strategy to quickly identify document clusters where can extract high-quality QA pairs for training. This iterative framework significantly reduces computational costs while improving model performance much. Experiments on AutoMathText, KnowledgePile and StackOverflow across 13 downstream tasks demonstrate that $\texttt{EQUAL}$ reduces computational costs by 5–10$\times$ while improving accuracy by 2.5\% on LLaMA-3.1-8B, Qwen2.5-7B and Mistral-7B. Code and data is available at https://anonymous.4open.science/r/EQUAL-DD20.

Scaling data and artificial neural networks has transformed AI, driving breakthroughs in language and vision. Whether similar principles apply to modeling brain activity remains unclear. Here we leveraged a dataset of 3.3 million neurons from the visual cortex of 78 mice across 323 sessions, totaling more than 150 billion neural tokens recorded during natural movies, images and parametric stimuli, and behavior. We train multi-modal, multi-task transformer models (1M–300M parameters) that support three regimes flexibly at test time: neural prediction (predicting neuronal responses from sensory input and behavior), behavioral decoding (predicting behavior from neural activity), neural forecasting (predicting future activity from current neural dynamics), or any combination of the three. We find that performance scales reliably with more data, but gains from increasing model size saturate -- suggesting that current brain models are limited by data rather than compute. This inverts the standard AI scaling story: in language and computer vision, massive datasets make parameter scaling the primary driver of progress, whereas in brain modeling -- even in the mouse visual cortex, a relatively simple and low-resolution system -- models remain data-limited despite vast recordings. These findings highlight the need for richer stimuli, tasks, and larger-scale recordings to build brain foundation models. The observation of systematic scaling raises the possibility of phase transitions in neural modeling, where larger and richer datasets might unlock qualitatively new capabilities, paralleling the emergent properties seen in large language models.

Multimodal reasoning is a dynamic process that requires synergistic coordination of language and vision. However, current approaches to multimodal interleaved generation fall short of providing a generalizable recipe that productively engages text and vision to advance reasoning. We introduce ThinkMorph, a unified thinking model capable of effective interleaved reasoning. By constructing a high-quality pipeline for generating interleaved reasoning data for training unified models, we enable ThinkMorph to generate multimodal reasoning traces where language and vision mutually advance each other. ThinkMorph delivers substantial gains on vision-centric reasoning, including +11.53\% on visual search and +38.75\% on jigsaw assembly over the base model. It also reaches 80.33\% on MMVP and 52.67\% on SAT, indicating strong generalization. The improvements are large enough to close the gap with, and in some cases even surpass, leading large-scale or proprietary VLMs. Moreover, ThinkMorph reveals \emph{emergent properties} indicative of higher-level multimodal intelligence. These include unseen visual manipulation skills during finetuning, such as zoom-in and image inpainting, as well as autonomous reasoning mode switching, wherein a model trained exclusively on interleaved data chooses to engage in text-only reasoning due to the nature of the task, for instance. We show that this ability to think in text, vision, and multimodality opens new avenues for test-time scaling, allowing ThinkMorph to \textit{effectively scale and aggregate thoughts across three reasoning modes}. These findings suggest promising directions for future work to characterize the emergent capabilities of unified models for multimodal reasoning.

Character image animation has rapidly advanced with the rise of digital humans. However, existing methods rely largely on 2D-rendered pose images for motion guidance, which limits generalization and discards essential 4D information for open-world animation. To address this, we propose MTVCraft (Motion Tokenization Video Crafter), the first framework that directly models raw 3D motion sequences (i.e., 4D motion) for character image animation. Specifically, we introduce 4DMoT (4D motion tokenizer) to quantize 3D motion sequences into 4D motion tokens. Compared to 2D-rendered pose images, 4D motion tokens offer more robust spatial-temporal cues and avoid strict pixel-level alignment between pose images and the character, enabling more flexible and disentangled control. Next, we introduce MV-DiT (Motion-aware Video DiT). By designing unique motion attention with 4D positional encodings, MV-DiT can effectively leverage motion tokens as 4D compact yet expressive context for character image animation in the complex 4D world. We implement MTVCraft on both CogVideoX-5B (small scale) and Wan-2.1-14B (large scale), demonstrating that our framework is easily scalable and can be applied to models of varying sizes. Experiments on the TikTok and Fashion benchmarks demonstrate our state-of-the-art performance. Moreover, powered by robust motion tokens, MTVCraft showcases unparalleled zero-shot generalization. It can animate arbitrary characters in both single and multiple settings, in full-body and half-body forms, and even non-human objects across diverse styles and scenarios. Hence, it marks a significant step forward in this field and opens a new direction for pose-guided video generation.

Effective environment modeling is the foundation for autonomous driving, underpinning tasks from perception to planning. However, current paradigms often inadequately consider the feedback of ego motion to the observation, which leads to an incomplete understanding of the driving process and consequently limits the planning capability. To address this issue, we introduce a novel ego-scene interactive modeling paradigm. Inspired by human recognition, the paradigm represents ego-scene interaction as the scene flow relative to the ego-vehicle. This conceptualization allows for modeling ego-motion feedback within a feature learning pattern, advantageously utilizing existing log-replay datasets rather than relying on scenario simulations. We specifically propose FlowAD, a general flow-based framework for autonomous driving. Within it, an ego-guided scene partition first constructs basic flow units to quantify scene flow. The ego-vehicle's forward direction and steering velocity directly shape the partition, which reflects ego motion. Then, based on flow units, spatial and temporal flow predictions are performed to model dynamics of scene flow, encompassing both spatial displacement and temporal variation. The final task-aware enhancement exploits learned spatio-temporal flow dynamics to benefit diverse tasks through object and region-level strategies. We also propose a novel Frames before Correct Planning (FCP) metric to assess the scene understanding capability. Experiments in both open and closed-loop evaluations demonstrate FlowAD's generality and effectiveness across perception, end-to-end planning, and VLM analysis. Notably, FlowAD reduces 19\% collision rate over SparseDrive with FCP improvements of 1.39 frames (60\%) on nuScenes, and achieves an impressive driving score of 51.77 on Bench2Drive, proving the superiority. Code, model, and configurations will be released.

Language models often show little to no improvement (i.e., “saturation”) when trained via vanilla supervised fine-tuning (SFT) on data similar to what they saw in their training set (e.g., MATH). We introduce a new fine-tuning strategy, STAT, to train such a student model by using the metacognition ability of a stronger large language model (LLM) as the teacher. The teacher uses the task dataset to create a list of skills needed for the task, and then labels each data point with its required skills (Didolkar et al., 2024). By monitoring the student’s answers, the teacher creates a Missing-Skill-Profile for the student, tracking how often they failed to apply each skill in their responses. We use this idea to build a modified training set in one of two ways. In STAT-Sel, the teacher uses an existing set of training examples but adaptively reweights them according to the Missing-Skill-Profile. In STAT-Syn, the teacher synthesizes additional examples involving missing skills. Across extensive experiments on Llama and Qwen models, our methods yield improvements of up to 7.5% on MATH, whereas SFT provides only limited gains. Furthermore, STAT enhances performance on out-of-distribution benchmarks (e.g., AIME24/25, AMC23, etc.) by an average of 4.6%. Crucially, we find that STAT is complementary to RL via GRPO (Shao et al., 2024): after the model is improved using STAT to address skill gaps, GRPO continues to add further gains. We conclude that skill-targeted adaptive training should broadly improve current training pipelines.

Knowledge distillation is an efficient strategy to use data generated by large teacher language models to train smaller “capable” student models, but selecting the optimal teacher for a specific student-task combination requires expensive trial-and-error. We propose a lightweight score called GRACE to quantify how effective a teacher will be when post-training a student model to solve math problems. GRACE efficiently measures distributional properties of student gradients, and it can be computed without access to a verifier, teacher logits, teacher internals, or test data. From an information-theoretic perspective, GRACE measures leave-one-out stability in gradient-based algorithms, directly connecting it to the generalization performance of distilled student models. On GSM8K and MATH, GRACE correlates strongly (up to 86%) with the performance of the distilled Llama and OLMo students. In particular, training on GRACE-selected teacher provides at least a 6% improvement over naively using the best-performing teacher. We further demonstrate the utility of GRACE in providing guidance on crucial design choices in distillation, including (1) the best temperature to use when generating from the teacher, (2) the best teacher to use given a size constraint, and (3) the best teacher to use within a specific model family. Altogether, our findings demonstrate that GRACE can efficiently and effectively identify the most compatible teacher for a given student and provide fine-grained guidance on how to perform distillation.

Hybrid model architectures that combine computational primitives (e.g., Attention, MLP) in different ratios have shown promising performance beyond Transformers. Some studies have shown that different interleavings of primitives can affect model quality as well. However, prior works explore the hybrid model architecture design space manually. Due to the large design space and training costs, discovering hybrid models that combine key computational primitives for pre-training is challenging. In this work, we take a principled approach in designing a modular hybrid model architecture search framework — Composer. Composer explores model architectures at a small scale and extrapolates the top-performing model architectures to a larger scale using our proposed scaling strategies. Using Composer, we discover new hybrid LLM architectures that outperform Llama 3.2. Compared to Llama 3.2 and previous state-of-the-art baselines, the new model architectures consistently reduce validation loss at parameter scales of 350M-3B and improve evaluation accuracy on the downstream tasks by up to 2.8-8.3% (1.1-3.1% on average) while improving both training and inference efficiency.

We introduce _String Seed of Thought (SSoT)_, a novel prompting method for LLMs that improves _Probabilistic Instruction Following (PIF)_. We define PIF as a task requiring an LLM to select its answer from a predefined set of options, each associated with a specific probability, such that the empirical distribution of the generated answers aligns with the target distribution when prompted multiple times. While LLMs excel at tasks with single, deterministic answers, they often fail at PIF, exhibiting biases problematic for applications requiring non-deterministic behaviors, such as human-behavior simulation, content diversification, and multiplayer games. It also harms the diversity of generated responses, a crucial factor in test-time scaling, by causing the outputs to collapse into a limited set of answers. To address this, we propose SSoT, a simple prompting method that instructs an LLM to first output a random string to generate sufficient entropy. SSoT also instructs the LLM to extract randomness by manipulating this string to derive a final answer, thereby preserving diversity while adhering to specific constraints. We demonstrate that SSoT significantly improves the PIF performance of LLMs, approaching the ideal performance of a pseudo-random number generator. Notably, our experiments on NoveltyBench show SSoT's benefits extend beyond closed-set tasks to open-ended tasks by enhancing response diversity.

Large Language Models (LLMs) achieve state-of-the-art performance but are costly to deploy in resource-constrained environments. Pruning with $n:m$ semi-structured sparsity reduces computation and enables hardware acceleration, yet existing methods face a trade-off: one-shot approaches are efficient but heuristic, while optimization-based methods are accurate but expensive. We introduce \textbf{HyperPrune}, a resource-efficient framework that directly optimizes $n:m$ sparsity. A lightweight hypernetwork, shared across layers and conditioned on learnable embeddings, generates structured masks in a one-shot, layer-wise manner. \textit{Continual pruning} preserves cross-layer knowledge, and \textit{feature outlier regularization} retains critical activations, unifying the strengths of heuristic and optimization-based methods. Experiments on LLaMA-7B to 70B show state-of-the-art accuracy–sparsity trade-offs on a single A100 GPU, achieving higher efficiency, accuracy, and scalability than prior approaches. HyperPrune offers a practical, scalable, and hardware-friendly solution for structured LLM pruning.

Large Language Models (LLMs) excel across diverse applications but remain impractical for edge deployment due to severe memory bottlenecks at the edge devices. We propose Equilibrium Language Models (ELMs), a novel compression framework that replaces groups of Transformer layers with a lightweight fixed-point network, reinterpreting deep computation as solving for an equilibrium state. To achieve ELMs, We introduce *Group Pruning Policy Optimization*, which automatically learns optimal pruning intervals. Moreover, we propose *One-Step KV-Cache*, which drastically reduces memory overhead by storing only the final iteration cache without compromising the accuracy, to enable effective deployment at the edge devices. Across different tasks such as common sense reasoning, mathematical problem solving, and code generation, ELMs prune 28\% of parameters while retaining 99\% of the accuracy of dense fine-tuned LLMs, establishing a new direction for memory-efficient edge deployment of large models.

Speculative sampling (SpS) has been successful in accelerating the decoding throughput of auto-regressive large language models by leveraging smaller draft models. SpS strictly enforces the generated distribution to match that of the verifier LLM. This is unnecessarily restrictive as slight variation of the verifier's distribution, such as sampling with top-$k$ or temperature, would also be acceptable. Typical acceptance sampling (TAS) alleviates this issue by accepting more tokens using entropy-based heuristics. However, this approach distorts the verifier distribution, potentially degrading output quality when the verifier encodes critical information. In this work, we formalize the speculative sampling algorithm through the lens of constrained optimization. Based on this formulation, we propose **Cactus** (**c**onstrained **ac**cep**t**ance spec**u**lative **s**ampling), a method that guarantees controlled divergence from the verifier distribution and increasing acceptance rates. Empirical results across a wide range of benchmarks confirm the effectiveness of our approach.

Existing adversarial attacks on large Vision-Language Models (VLMs) often struggle with limited transferability to black-box models or produce perceptible artifacts that are easily detected. This paper presents Progressive Semantic Infusion (PSI), a diffusion-based attack that progressively aligns and infuses natural target semantics. To improve transferability, PSI leverages diffusion priors to better align adversarial examples with the natural image distribution and employs progressive alignment to mitigate overfitting on a single fixed surrogate objective. To enhance stealthiness, PSI embeds source-aware cues during denoising to preserve visual fidelity and avoid detectable artifacts. Experiments show that PSI effectively attacks open-source, adversarially trained, and commercial VLMs, including GPT-5 and Grok-4, surpassing existing methods in both transferability and stealthiness. Our findings highlight a critical vulnerability in modern vision-language systems and offer valuable insights towards building more robust and trustworthy multimodal models.

As the demand for comprehensive evaluations of diverse model capabilities steadily increases, benchmark suites have correspondingly grown significantly in scale. Despite notable advances in redundancy reduction and subset-level performance prediction, a systematic framework that effectively integrates these methods to ensure both prediction accuracy and ranking consistency is still largely elusive. In this paper, we first perform a sample-level analysis of benchmark redundancy and identify several highly similar samples that can be eliminated. Besides, we frame benchmark compression as an optimization problem with the aim of score reconstruction. Building on these, we then propose EssenceBench, a coarse-to-fine framework utilizing an iterative Genetic Algorithm (GA), which takes the advantages of fitness-based subset search and attribution-based sample search. Compared to previous methods, our approach yields superior compression results with lower reconstruction error and markedly higher efficiency. In particular, on the HellaSwag benchmark (10K samples), our method preserves the ranking of all models shifting within 5% using 25$\times$ fewer samples, and achieves 95% ranking preservation shifting within 5% using only 200$\times$ fewer samples. The source code will be made available upon acceptance of the paper.

While adversarial fine-tuning can enhance the robustness of vision-language models (VLMs), such approaches are computationally expensive. Adversarial prompt tuning has emerged as a practical alternative. However, existing methods are limited by their reliance on vulnerable continuous image features. To mitigate the vulnerability in the feature representation, we propose **DEFEAT** (**D**iscrete Lat**E**nt **F**eatur**E** based **A**dversarial **T**raining), a robust prompt tuning framework for VLMs. Specifically, the DEFEAT method introduces a perturbation discrete shield module that reconstructs discrete latent features and designs a logits fusion strategy, substantially reducing the discrepancy between clean and adversarial image representations. Moreover, the DEFEAT method integrates prompt tuning with adversarial training while applying regularization from learnable prompts to hand-crafted prompts, further enhancing the adversarial robustness. Extensive experiments across 15 datasets validate the effectiveness of the proposed DEFEAT method among existing adversarial prompt tuning methods.

Large Language Models (LLMs) demonstrate remarkable capabilities in solving complicated reasoning tasks by imitating the human thinking process from human languages. However, even the most capable LLMs can still fail in tasks that are simple for humans. To understand the gap, we construct structural causal models of next-token predictors in human languages. As language is primarily a tool for humans to share knowledge instead of thinking, modeling human thinking from languages can integrate language expression biases into LLMs. More specifically, we show that LLMs can fail to understand implicit expressions -- expression patterns occur less frequently during training. Consequently, LLMs can easily overlook critical information when biased by implicit expressions. We verify our theoretical claims with carefully constructed realistic datasets containing implicit expressions. Furthermore, we also propose a prompt-level intervention to instruct LLMs to carefully expand and focus on all the expressions available. The empirical success of the prompt-level intervention across 11 tasks and 4 representative LLMs, along with the improvements over general reasoning tasks, reaffirms our findings.

Competitive programming has emerged as a critical benchmark for evaluating the reasoning and coding capabilities of Large Language Models (LLMs). Despite impressive progress on existing benchmarks, we argue that current evaluations overstate model proficiency, masking a substantial gap between LLMs and elite human programmers. This gap arises from two key limitations: insufficient difficulty and scope of benchmark problems, and evaluation bias from low-quality test cases. To address these shortcomings, we present **AetherCode**, a new benchmark that draws problems from premier programming competitions such as IOI and ICPC, offering broader coverage and higher difficulty. AetherCode further incorporates comprehensive, expert-validated test suites built through a hybrid of automated generation and human curation, ensuring rigorous and reliable assessment. By combining challenging problem design with robust evaluation, AetherCode provides a more faithful measure of LLM capabilities and sets a new standard for future research in code reasoning.

Conventional frame-based cameras often struggle with stereo depth estimation in rapidly changing scenes. In contrast, bio-inspired spike cameras emit asynchronous events at microsecond-level resolution, providing an alternative sensing modality. However, existing methods lack specialized stereo algorithms and benchmarks tailored to the spike data. To address this gap, we propose SpikeStereoNet, a brain-inspired framework to estimate stereo depth directly from raw spike streams. The model fuses raw spike streams from two viewpoints and iteratively refines depth estimation through a recurrent spiking neural network (RSNN) update module. To benchmark our approach, we introduce a large-scale synthetic spike stream dataset and a real-world stereo spike dataset with dense depth annotations. SpikeStereoNet outperforms existing methods on both datasets by leveraging spike streams' ability to capture subtle edges and intensity shifts in challenging regions such as textureless surfaces and extreme lighting conditions. Furthermore, our framework exhibits strong data efficiency, maintaining high accuracy even with substantially reduced training data.