Increasing the batch size during training --- a “batch ramp'' --- is a promising strategy to accelerate large language model pretraining. While for SGD, doubling the batch size can be equivalent to halving the learning rate, the optimal strategy for adaptive optimizers like Adam is less clear. As a result, any batch-ramp scheduling, if used at all, is typically tuned heuristically. This work develops a principled framework for batch-size scheduling and introduces Seesaw: whenever a standard scheduler would halve the learning rate, Seesaw instead multiplies it by $1/\sqrt{2}$ and doubles the batch size, preserving loss dynamics while reducing serial steps. Theoretically, we provide, to our knowledge, the first finite-sample proof of equivalence between learning-rate decay and batch-size ramp-up for SGD on noisy linear regression, and we extend this equivalence to normalized SGD, a tractable proxy for Adam, under a variance-dominated regime observed in practice. Empirically, on 150M/300M/600M-parameter models trained at Chinchilla scale using a constant (critical) batch size, Seesaw matches cosine decay at equal FLOPs while reducing wall-clock time by $\approx 36\%$, approaching the theoretical limit implied by our analysis.
论文检索
输入标题、作者或关键词，从 12,113 篇学术成果中精准定位
Mathematical problem synthesis shows promise in resolving data exhaustion, contamination, and leakage for AI training and evaluation. Despite enormous efforts, an **expressiveness-validity-complexity trilemma** remains an open question. Existing methods either lack whole-process verifiability, are constrained to a particular domain, or are bounded by external models. This paper breaks the trilemma by proposing the framework of **DExploration** _(**D**eductive **Exploration**)_, which formulates problem synthesis as a step-by-step exploration process instead of one-shot generation. Agents are equipped with three simple yet powerful atomic actions: _introducing_ variables/hypotheses, _deducing_ new facts, and _submitting_ derived facts. The entire exploration process is formally verified by Lean 4, which encompasses most mathematical domains up to the research level. Once a conclusion is submitted, the framework outputs a formal statement with guaranteed provability, reducing the need for external models. To bootstrap training data for DExploration, we propose **Exploratory Transformation** to distill exploration trajectories from existing large-scale theorem-proving data. It rewrites formal proofs into a deductive style, parses dependencies among variables, hypotheses, and proof steps, then reassembles them into exploration trajectories by a topological order. Experiments validate the effectiveness and efficiency of our methods, achieving an improved success rate ($40.70\\% \mapsto 54.52\\%$), reduced token cost ($52.9\text{K} \mapsto 8.8\text{K}, 83\\%\downarrow$), broader complexity and difficulty distributions, and Pareto optimality. In $2726$ valid generations, three state-of-the-art provers fail on $60$ (Pass@4) and $8$ (Pass@64).
Applications · Language, Speech and Dialog
Recent advances in large reasoning language models (LRMs) rely on test-time scaling, which extends long chain-of-thought (CoT) generation to solve complex tasks. However, overthinking in long CoT not only slows down the efficiency of problem solving, but also risks accuracy loss due to the extremely detailed or redundant reasoning steps. We propose a simple yet effective method that allows LLMs to self-truncate CoT sequences by early exit during generation. Instead of relying on fixed heuristics, the proposed method monitors model behavior at potential reasoning transition points and dynamically terminates the next reasoning chain's generation when the model exhibits high confidence in a trial answer. Our method requires no additional training and can be seamlessly integrated into existing o1-like reasoning LLMs. Experiments on 10 reasoning benchmarks (e.g., GSM8K, MATH-500, AMC, GPQA, AIME and LiveCodeBench) show that the proposed method is consistently effective on 11 cutting-edge reasoning LLMs of varying series and sizes, reducing the length of CoT sequences by an average of 19.1% to 80.1% while improving accuracy by 0.3% to 5.0%.
High-resolution structure determination by cryo-electron microscopy (cryo-EM) requires the accurate fitting of an atomic model into an experimental density map. Traditional refinement pipelines like Phenix.real_space_refine and Rosetta are computationally expensive, demand extensive manual tuning, and present a significant bottleneck for researchers. We present CryoNet.Refine, an end-to-end, deep learning framework that automates and accelerates molecular structure refinement. Our approach utilizes a one-step diffusion model that integrates a density-aware loss function with robust stereochemical restraints, enabling it to rapidly optimize a structure against the experimental data. CryoNet.Refine stands as a unified and versatile solution capable of refining not only protein complexes but also nucleic acids (DNA/RNA) and their assemblies. In benchmarks against Phenix.real_space_refine, CryoNet.Refine consistently yields substantial improvements in both model–map correlation and overall model geometric quality. By offering a scalable, automated, and powerful alternative, CryoNet.Refine is poised to become an essential tool for next-generation cryo-EM structure refinement. Web server: https://cryonet.ai/refine; Source code: https://github.com/kuixu/cryonet.refine.
Reinforcement Learning · Everything Else
Designing robust reinforcement learning (RL) agents in the presence of imperfect reward signals remains a core challenge. In practice, agents are often trained with proxy rewards that only approximate the true objective, leaving them vulnerable to reward hacking, where high proxy returns arise from unintended or exploitative behaviors. Recent work formalizes this issue using r-correlation between proxy and true rewards, but existing methods like occupancy-regularized policy optimization (ORPO) optimize against a fixed proxy and do not provide strong guarantees against broader classes of correlated proxies. In this work, we formulate reward hacking as a robust policy optimization problem over the space of all r-correlated proxy rewards. We derive a tractable max-min formulation, where the agent maximizes performance under the worst-case proxy consistent with the correlation constraint. We further show that when the reward is a linear function of known features, our approach can be adapted to incorporate this prior knowledge, yielding both improved policies and interpretable worst-case rewards. Experiments across several environments show that our algorithms consistently outperform ORPO in worst-case returns, and offer improved robustness and stability across different levels of proxy–true reward correlation. These results show that our approach provides both robustness and transparency in settings where reward design is inherently uncertain.
Computer Vision · Image and Video Generation
Diffusion transformers currently lead the field in high-quality video generation, but their slow iterative denoising process and prohibitive quadratic attention costs for long sequences create significant inference bottlenecks. While both step distillation and sparse attention mechanisms have shown promise as independent acceleration strategies, effectively combining these approaches presents critical challenges---training-free integration yields suboptimal results, while separately training sparse attention after step distillation requires prohibitively expensive high-quality video data. To overcome these limitations, we propose $\textit{BLADE}$, an innovative data-free joint training framework that introduces: (1) an Adaptive Block-Sparse Attention (ASA) mechanism for dynamically generating content-aware sparsity masks to focus computation on salient spatiotemporal features, and (2) a sparsity-aware step distillation paradigm, built upon Trajectory Distribution Matching (TDM), directly incorporates sparsity into the distillation process rather than treating it as a separate compression step and features fast convergence. We validate BLADE on text-to-video models like CogVideoX-5B and Wan2.1-1.3B, and our framework demonstrates remarkable efficiency gains across different scales. On Wan2.1-1.3B, BLADE achieves a 14.10$\times$ end-to-end inference acceleration over a 50-step baseline. Moreover, on models such as CogVideoX-5B with short video sequence lengths, our framework delivers a robust 8.89$\times$ speedup. Crucially, the acceleration is accompanied by a consistent quality improvement. On the VBench-2.0 benchmark, BLADE boosts the score of CogVideoX-5B to 0.569 (from 0.534) and Wan2.1-1.3B to 0.570 (from 0.563), results that are further corroborated by superior ratings in human evaluations.
Computer Vision · Vision Models & Multimodal
Parsing raster-based scientific diagrams into structured representations is critical for editability and reusability. However, existing multimodal LLMs (MLLMs) struggle with the diverse visual primitives, complex structural layouts, and strict syntax involved. To address this, we introduce DaVinci, a novel MLLM that learns diagram parsing based on a two-stage framework—supervised learning of visual primitives followed by reinforcement learning of their structural relationships. Our model learns visual-structural syntax through supervised training on TikZ30K, a newly curated dataset of high-quality diagram-TikZ code pairs that features abundant visual primitives and structurally optimized drawing sequences. We further refine the model via reinforcement learning, guided by a hybrid reward function that jointly optimizes for visual fidelity, structural consistency, and code correctness. Extensive experiments show that DaVinci significantly outperforms existing open-source MLLMs and surpasses leading proprietary models like GPT-5 and Claude-Sonnet-4.
Humanoid robots require precise locomotion and dexterous manipulation to perform challenging locomanipulation tasks. Yet existing approaches, modular or end-to-end, are deficient in manipulation-aware locomotion. This confines the robot to a limited workspace, preventing it from performing large-space loco-manipulation. We attribute this to: (1) the challenge of acquiring loco-manipulation knowledge due to the scarcity of humanoid teleoperation data, and (2) the difficulty of faithfully and reliably executing locomotion commands, stemming from the limited precision and stability of existing RL controllers. To acquire richer loco-manipulation knowledge, we propose a unified latent learning framework that enables Vision-Language-Action (VLA) system to learn from low-cost action-free egocentric videos. Moreover, an efficient data collection pipeline is devised to augment the dataset and scale the benefits. To more precisely execute the desired locomotion commands, we present a loco–manipulation–oriented (LMO) RL policy specifically tailored for accurate and stable core loco-manipulation movements, such as advancing, turning, and squatting. Building on these components, we introduce WholeBodyVLA, a unified framework for humanoid loco-manipulation. To the best of our knowledge, WholeBodyVLA is one of its kind enabling large-space humanoid loco–manipulation. It is verified via comprehensive experiments on the AgiBot X2 humanoid, outperforming prior baseline by 21.3%. It also demonstrates strong generalization and high extensibility across a broad range of tasks. Code and checkpoints would be made public.
Reinforcement Learning · Planning
Large language model (LLM)-based agents struggle to generalize to novel and complex environments, such as unseen websites or new sets of functions, due to a fundamental mismatch between their pre-training and test-time conditions. This challenge stems from two distinct failure modes: a syntactic misunderstanding of environment-specific components like observation formats, and a semantic misunderstanding of state-transition dynamics, which are only revealed at test time. To address these issues, we propose two distinct strategies for adapting LLM agents by leveraging environment-specific information from interaction that is available during deployment. First, an online syntactic alignment (SA) method parameterizes environmental nuances by learning a lightweight adaptation vector that biases the model's output distribution, enabling rapid alignment with an environment response format. Second, a deployment-time dynamics grounding (DG) method employs a persona-driven exploration phase to systematically probe and learn the environment's causal dynamics before task execution, equipping the agent with an in-context world model. We evaluate these strategies across diverse agentic benchmarks, including function calling and web navigation. Our empirical results show the effectiveness of both strategies across all benchmarks with minimal computational cost. We find that dynamics grounding is particularly effective in complex environments where unpredictable dynamics pose a major obstacle, demonstrating a robust path toward more generalizable and capable LLM-based agents. For example, on the WebArena multi-site split, this method increases the agent's success rate from 2\% to 23\%. We release our code.
Reinforcement Learning · Everything Else
Deep reinforcement learning has achieved impressive success in control tasks. However, its policies, represented as opaque neural networks, are often difficult for humans to understand, verify, and debug, which undermines trust and hinders real-world deployment. This work addresses this challenge by introducing a novel approach for programmatic control policy discovery, called **M**ultimodal Large **L**anguage Model-assisted **E**volutionary **S**earch (MLES). MLES utilizes multimodal large language models as programmatic policy generators, combining them with evolutionary search to automate policy generation. It integrates visual feedback-driven behavior analysis within the policy generation process to identify failure patterns and guide targeted improvements, thereby enhancing policy discovery efficiency and producing adaptable, human-aligned policies. Experimental results demonstrate that MLES achieves performance comparable to Proximal Policy Optimization (PPO) across two standard control tasks while providing transparent control logic and traceable design processes. This approach also overcomes the limitations of predefined domain-specific languages, facilitates knowledge transfer and reuse, and is scalable across various tasks, showing promise as a new paradigm for developing transparent and verifiable control policies. Code is publicly available at https://github.com/QingL2000/MLES.
Computer Vision · Image and Video Generation
Latent Diffusion Models (LDMs) have recently shown great potential for image restoration owing to their powerful generative priors. However, directly applying them to ultra-high-definition image restoration (UHD-IR) often results in severe global inconsistencies and loss of fine-grained details, primarily caused by patch-based inference and the information bottleneck of the VAE. To overcome these issues, we present FreeAdapt, a plug-and-play framework that unleashes the capability of diffusion priors for UHD-IR. The core of FreeAdapt is a training-free Frequency Feature Synergistic Guidance (FFSG) mechanism, which introduces guidance at each denoising step during inference time. It consists of two modules: 1) Frequency Guidance (FreqG) selectively fuses phase information from a reference image in the frequency domain to enforce structural consistency across the entire image; 2) Feature Guidance (FeatG) injects global contextual information into the self-attention layers of the U-Net, effectively suppressing unrealistic textures in smooth regions and preserving local detail fidelity. In addition, FreeAdapt includes an optional VAE fine-tuning module, where skip connection further enhances the reconstruction of fine-grained textures. Extensive experiments demonstrate that our method achieves superior quantitative performance and visual quality compared to state-of-the-art UHD-IR approaches, and consistently delivers strong gains across multiple LDM-based backbones.
Applications · Robotics
Aerial Vision-Language Navigation (VLN) seeks to guide UAVs by leveraging language instructions and visual cues, establishing a new paradigm for human-UAV interaction. However, the collection of VLN data demands extensive human effort to construct trajectories and corresponding instructions, hindering the development of large-scale datasets and capable models. To address this problem, we propose OpenFly, a comprehensive platform for aerial VLN. Firstly, OpenFly integrates 4 rendering engines and advanced techniques for diverse environment simulation, including Unreal Engine, GTA V, Google Earth, and 3D Gaussian Splatting (3D GS). Particularly, 3D GS supports real-to-sim rendering, further enhancing the realism of our environments. Secondly, we develop a highly automated toolchain for aerial VLN data collection, streamlining point cloud acquisition, scene semantic segmentation, flight trajectory creation, and instruction generation. Thirdly, based on the toolchain, we construct a large-scale aerial VLN dataset with 100k trajectories, covering samples of diverse scenarios and assets across 18 scenes. Moreover, we propose OpenFly-Agent, a keyframe-aware VLN model emphasizing key observations to promote performance and reduce computations. For benchmarking, extensive experiments and analyses are conducted, where our navigation success rate outperforms others by 14.0\% and 7.9\% on the seen and unseen scenarios, respectively. The toolchain, dataset, and codes will be open-sourced.
Deep Learning · Graph Neural Networks
Weight-space models learn directly from the parameters of neural networks, enabling tasks such as predicting their accuracy on new datasets. Naive methods -- like applying MLPs to flattened parameters -- perform poorly, making the design of better weight-space architectures a central challenge. While prior work leveraged permutation symmetries in standard networks to guide such designs, no analogous analysis or tailored architecture yet exists for Kolmogorov–Arnold Networks (KANs). In this work, we show that KANs share the same permutation symmetries as MLPs, and propose the KAN-graph, a graph representation of their computation. Building on this, we develop WS-KAN, the first weight-space architecture that learns on KANs, which naturally accounts for their symmetry. We analyze WS-KAN’s expressive power, showing it can replicate an input KAN’s forward pass - a standard approach for assessing expressiveness in weight-space architectures. We construct a comprehensive ``zoo'' of trained KANs spanning diverse tasks, which we use as benchmarks to empirically evaluate WS-KAN. Across all tasks, WS-KAN consistently outperforms structure-agnostic baselines, often by a substantial margin.
Deep Learning · Everything Else
Large Language Models (LLMs) have recently improved mathematical reasoning through Reinforcement Learning with Verifiable Reward (RLVR). However, existing RLVR algorithms require large query budgets, making annotation costly. We investigate whether fewer but more informative queries can yield similar or superior performance, introducing active learning (AL) into RLVR. We identify that classic AL sampling strategies fail to outperform random selection in this setting, due to ignoring \textbf{objective uncertainty} when only selecting by subjective uncertainty. This work proposes an \textbf{uncertainty consistency} metric to evaluate how well subjective uncertainty aligns with objective uncertainty. In the offline setting, this alignment is measured using the Point-Biserial Correlation Coefficient (PBC). For online training, because of limited sampling and dynamically shifting output distributions, PBC estimation is difficult. Therefore, we introduce a new online variant, computed from normalized advantage and subjective uncertainty. Theoretically, we prove that the online variant is strictly negatively correlated with offline PBC and supports better sample selection. Experiments show our method consistently outperforms random and classic AL baselines, achieving full-dataset performance while training on only 30\% of the data, effectively reducing the cost of RLVR for reasoning tasks.\footnote{The code is available at \hyperref[https://github.com/yihao-123/uncertainty-consistency]{https://github.com/yihao-123/uncertainty-consistency}. }
Computer Vision · Image and Video Generation
Computational replication of Chinese calligraphy, a cornerstone of cultural heritage, remains challenging. Existing methods split into two flawed camps: some render high-quality isolated characters yet miss page-level aesthetics (ligatures, spacing, scale), while others attempt page/column synthesis but sacrifice calligraphic correctness. We introduce UniCalli, a unified diffusion framework for column-level recognition and generation. Training both tasks in one model is deliberate: recognition constrains the generator to preserve character identity and stroke structure, while generation supplies strong style/layout priors—together fostering concept-level abstractions (radicals, stroke configurations) that improve both tasks under long-tail, limited-label regimes. We curate a dataset of 8,000+ digitized pieces, with ~4,000 densely annotated (script labels, character boxes, transcriptions). UniCalli employs asymmetric noising and a rasterized box map to inject spatial priors, and is trained on a mix of synthetic, labeled, and unlabeled data. The model is robust to rare styles, better disentangles style from script, and attains state-of-the-art generative quality with clear gains in ligature continuity and layout fidelity, alongside stronger recognition. The framework extends to other ancient scripts, demonstrated by successful transfer to Oracle bone inscriptions and Egyptian hieroglyphs. Code and data will be released.
Training large language models (LLMs) for complex reasoning via Reinforcement Learning with Verifiable Rewards (RLVR) is effective but limited by reliance on costly, domain-specific supervision. We explore Reinforcement Learning from Internal Feedback (RLIF), a framework that enables LLMs to learn from intrinsic signals without external rewards or labeled data. We propose Intuitor, an RLIF method that uses a model's own confidence—termed self-certainty—as its sole reward signal. Intuitor replaces external rewards in Group Relative Policy Optimization (GRPO) with self-certainty scores, enabling fully unsupervised learning. Experiments demonstrate that Intuitor matches GRPO's performance on mathematical benchmarks while achieving better generalization to out-of-domain tasks like code generation, without requiring gold solutions or test cases. Our findings show that intrinsic model signals can drive effective learning across domains, offering a scalable alternative to RLVR for autonomous AI systems where verifiable rewards are unavailable. Code is available at https://github.com/sunblaze-ucb/Intuitor
Applications · Physics
Crystal property prediction, governed by quantum mechanical principles, is computationally prohibitive to solve exactly for large many-body systems using traditional density functional theory. While machine learning models have emerged as efficient approximations for large-scale applications, their performance is strongly influenced by the choice of atomic representation. Although modern graph-based approaches have progressively incorporated more structural information, they often fail to capture long-range atomic interactions due to finite receptive fields and local encoding schemes. This limitation leads to distinct crystals being mapped to identical representations, hindering accurate property prediction. To address this, we introduce PRDNet that leverages unique reciprocal-space diffraction besides graph representations. To enhance sensitivity to elemental and environmental variations, we employ a data-driven pseudo-particle to generate a synthetic diffraction pattern. PRDNet ensures full invariance to crystallographic symmetries. Extensive experiments are conducted on Materials Project, JARVIS-DFT, and MatBench, demonstrating that the proposed model achieves state-of-the-art performance. The code is openly available at \url{https://github.com/Bin-Cao/PRDNet}.
Computer Vision · Image and Video Generation
Existing diffusion-based object removal and inpainting methods often fail to recover the fine structural and textural details of small objects. This is primarily due to the VAE encoder’s downsampling, which inevitably compresses small masked regions and causes significant detail loss, while the decoder’s upsampling alone cannot fully restore the lost fine details. However, the adverse effects of this fixed compression can be mitigated by enlarging the perspective of these regions. To this end, we propose ReFocusEraser, a two-stage framework for small object removal that combines camera-adaptive zoom-in inpainting with robust context- and shadow-aware repair. In Stage I, a camera-adaptive refocus mechanism magnifies masked regions, and a LoRA-tuned diffusion model ensures precise semantic alignment for accurate reconstruction. However, reintegrating these magnified inpainted regions into the original image introduces challenges due to VAE asymmetry, such as color shifts and seams. Stage II addresses these issues by fine-tuning an additional decoder to create a seam- and shadow-aware module that eliminates residual artifacts while preserving background consistency. Extensive experiments demonstrate that our proposed RefocusEraser achieves state-of-the-art performance, outperforming existing methods across benchmark datasets. Related code and data are available at https://github.com/ProAirVerse/ReFocusEraser.git.
We develop a theory of transfer learning in infinitely wide neural networks under gradient flow that quantifies when pretraining on a source task improves generalization on a target task. We analyze both (i) fine-tuning, when the downstream predictor is trained on top of source-induced features and (ii) a jointly rich setting, where both pretraining and downstream tasks can operate in a feature learning regime, but the downstream model is initialized with the features obtained after pre-training. In this setup, the summary statistics of randomly initialized networks after a rich pre-training are adaptive kernels which depend on both source data and labels. For (i), we analyze the performance of a readout for different pretraining data regimes. For (ii), the summary statistics after learning the target task are still adaptive kernels with features from both source and target tasks. We test our theory on linear and polynomial regression tasks as well as real datasets. Our theory allows interpretable conclusions on performance, which depend on the amount of data on both tasks, the alignment between tasks, and the feature learning strength.
Computer Vision · Vision Models & Multimodal
Humans can imagine and manipulate visual images mentally, a capability known as \textit{spatial visualization}. While many multi-modal benchmarks assess reasoning on visible visual information, the ability to infer unseen relationships through spatial visualization remains insufficiently evaluated as a spatial skill. This reliance on publicly sourced problems from IQ tests or math competitions risks data contamination and compromises assessment reliability. To this end, we introduce \textbf{\textit{SpatialViz-Bench}}, a comprehensive multi-modal benchmark for \textit{spatial visualization} with \emph{12} tasks across \emph{4} sub-abilities, comprising \emph{1,180} programmatically generated problems, a scalable framework that allows for expansion to ensure fair and continuously reliable evaluations. Our evaluation of \emph{27} Multi-modal Large Language Models (MLLMs) reveals wide performance variations, demonstrates the benchmark's strong discriminative power, and uncovers counter-intuitive findings: Chain-of-Thought (CoT) prompting paradoxically degrades accuracy on open-source models. Through statistical and qualitative analysis of error types, SpatialViz-Bench demonstrates that state-of-the-art MLLMs exhibit deficiencies in \textit{spatial visualization} tasks, thereby addressing a significant lacuna in the field.