❌

Reading view

↗️

Foaming photopolymers as a high-resolution biomimetic printing platform

✇Nature - Issue - nature.com science feeds
By: Detao Qin · Xianghui Liu · Baian Kuang · Yuzhe Zhang · Masateru Ito · Tatsuya Katsuno · Yuan Liu · Jianduo Zhang · Claudia Rosa · Meifang Zhu · Mikihito Takenaka · Hiroshi Imahori · Ganesh N. Pandian · Taiki Yanagishima · Easan Sivaniah

Nature, Published online: 09 September 2026; doi:10.1038/s41586-026-10968-9

Deep-foam photolithography uses light-controlled polymer foaming to create high-resolution, multifunctional microstructures with tunable optical, wetting and fluid-handling properties for advanced manufacturing applications.
  •  
  • ↗️
↗️

Denisovans from southwestern China and their subsistence strategies

✇Nature - Issue - nature.com science feeds
By: Qijun Ruan · Hao Li · Song Xing · Keliang Zhao · Jianhui Liu · Clément Zanolli · Luc Doyon · Davide Delpiano · Marco Peresani · Francesco d’Errico · Fabrice Demeter · Jean-Jacques Hublin · Peiyuan Xiao · Yuqing Wang · Zhenxiu Jia · Qingjiang Yang · Qiaomei Fu · Qiyahui Sun · Yuhao Zhao · Sungui Lin · Anchuan Fan · Youping Wang · Qingfeng Shao · Bo Li · Fahu Chen

Nature, Published online: 09 September 2026; doi:10.1038/s41586-026-10997-4

Evidence from Bianfu Cave shows specialized hunting, expedient stone-tool production and extensive bone use of Denisovans, providing new insights into their ecology, behaviour and cultural legacy in eastern Asia.
  •  
  • ↗️
↗️

CollectionLoRA: Collecting 50 Effects in 1 LoRA via Multi-Teacher On-Policy Distillation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Fangtai Wu · Hailong Guo · Shijie Huang · Jiayi Song · Yubo Huang · Mushui Liu · Zhao Wang · Yunlong Yu · Jiaming Liu · Ruihua Huang
arXiv:2605.25378v1 Announce Type: cross Abstract: Customized image editing aims to equip pre-trained diffusion models with specific visual effects using limited paired data, typically via Low-Rank Adaptation (LoRA). As the number of desired effects grows, storing and dynamically loading numerous these effect LoRAs significantly increases deployment overhead. Furthermore, current pipelines typically cascade these effect LoRAs with acceleration modules for fast generation, which triggers severe parameter interference and results in concept bleeding and style degradation. We propose CollectionLoRA, a multi-teacher on-policy distillation framework capable of distilling the concepts of up to 50 different effect LoRAs along with few-step generation capabilities into a single LoRA. This fundamentally resolves the feature interference issue and significantly reduces deployment costs. Specifically, the method introduces (i) a Probabilistic Dual-Stream Routing mechanism that enables the model to randomly switch between data sources during training, effectively enhancing its generalization in unseen scenarios; (ii) an Asymmetric Orthogonal Prompting strategy to achieve concept isolation within the prompt space; (iii) a Coarse-to-Fine Distillation Objective to mitigate the distribution gap between the teacher and student models. Extensive evaluations show that CollectionLoRA distills all customized effects and few-step generation into a single LoRA, reducing deployment overhead while achieving concept fidelity comparable to or better than independently trained teacher models.
  •  
  • ↗️
↗️

SURGE: Surrogate Gradient Adaptation in Binary Neural Networks

✇cs.AI, q-bio.NC updates on arXiv.org
By: Haoyu Huang · Boyu Liu · Linlin Yang · Yanjing Li · Yuguang Yang · Xuhui Liu · Canyu Chen · Zhongqian Fu · Baochang Zhang
arXiv:2605.10989v3 Announce Type: replace-cross Abstract: The training of Binary Neural Networks (BNNs) is fundamentally based on gradient approximation for non-differentiable binarization operations (e.g., sign function). However, prevailing methods including the Straight-Through Estimator (STE) and its improved variants, rely on hand-crafted designs that suffer from gradient mismatch problem and information loss induced by fixed-range gradient clipping. To address this, we propose SURrogate GradiEnt Adaptation (SURGE), a novel learnable gradient compensation framework with theoretical grounding. SURGE mitigates gradient mismatch through auxiliary backpropagation. Specifically, we design a Dual-Path Gradient Compensator (DPGC) that constructs a parallel full-precision auxiliary branch for each binarized layer, decoupling gradient flow via output decomposition during backpropagation. DPGC enables bias-reduced gradient estimation by leveraging the full-precision branch to estimate components beyond STE's first-order approximation. To further enhance training stability, we introduce an Adaptive Gradient Scaler (AGS) based on an optimal scale factor to dynamically balance inter-branch gradient contributions via norm-based scaling. Experiments on image classification, object detection, and language understanding tasks demonstrate that SURGE performs best over state-of-the-art methods.
  •  
  • ↗️
↗️

Automated Random Embedding for Practical Bayesian Optimization with Unknown Effective Dimension

✇cs.AI, q-bio.NC updates on arXiv.org
By: Hong Qian · Xiang Shu · Xiang Xia · Xuhui Liu · Yangde Fu · Bei Liang · Huibin Wang · Liang Dou
arXiv:2605.23473v2 Announce Type: replace-cross Abstract: Bayesian optimization is widely employed for optimizing complex black-box functions but struggles with the curse of dimensionality. Random embedding, as a dimension reduction strategy, simplifies tasks that possess the effective dimension by optimizing within a low-dimensional subspace. However, determining the effective dimension of a task in advance remains a significant challenge, which influences the selection of the subspace dimensionality and the optimization performance. Traditional methods use fixed subspace dimensions provided by experts or rely on trial and error to estimate subspace dimensions with resources consumed. To this end, this paper proposes an automated random embedding for high-dimensional Bayesian optimization with unknown effective dimension, called Dynamic Shared Embedding Bayesian Optimization (DSEBO). DSEBO starts with a low dimension and switches to a higher subspace if the solutions in the current subspace show preliminary convergence. DSEBO dynamically determines the dimension of the next subspace based on the quality of the solutions in different subspaces and shares the queried solutions with the new subspace for a better initialization. Theoretically, we derive a regret bound for DSEBO and demonstrate that DSEBO can better balance approximation and optimization errors. Extensive experiments on functions with dimensionality of varying magnitudes and real-world tasks with unknown effective dimensions reveal that, compared with state-of-the-art methods, alternating optimization across different subspaces results in significant improvements in high-dimensional optimization, both in terms of optimization regret and time.
  •  
  • ↗️
↗️

CoSPlay: Cooperative Self-Play at Test-Time with Self-Generated Code and Unit Test

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zhangyi Hu · Chenhui Liu · Tian Huang · Jindong Li · Yang Yang · Jiemin Wu · Zining Zhong · Menglin Yang · Yutao Yue
arXiv:2605.23491v2 Announce Type: replace-cross Abstract: Recently, Reinforcement Learning with Verifiable Rewards (RLVR) and Test-Time Scaling (TTS) have advanced LLM code generation through executable verification. Yet Ground-Truth Unit Tests (GT UTs) remain a bottleneck: SOTA RLVR methods require them for costly training, while existing TTS methods lose competitiveness without them. This motivates GT-free TTS, where existing methods directly use self-generated UTs to refine and select code candidates. Yet such UTs are often noisy or spuriously coupled with wrong code, and UT quality in turn cannot be validated without reliable code. The key challenge is therefore to jointly improve both. To this end, we present CoSPlay, a GT-free, training-free framework that jointly improves codes and UTs through cooperative self-play. It first explores diverse solution ideas and identifies their potential failure modes to produce discriminative UT ideas. It then uses bidirectional pass-count signals from the Code-UT execution matrix to iteratively prune or fix weak codes and refresh or replace unreliable UTs, letting the two pools co-evolve. Finally, when multiple codes remain tied at the highest pass count, it picks the final code from the largest output-consensus cluster, since correct codes agree on the same inputs while wrong codes diverge. Experiments on four challenging benchmarks show that CoSPlay on Qwen2.5-7B-Instruct improves average BoN from 22.1% to 33.2% and UT accuracy from 14.6% to 78.3%, matching or surpassing the RLVR model CURE-7B. When applied to CURE-7B, it further improves BoN by 5.7%. CoSPlay also generalizes across diverse backbones and outperforms GT-free TTS baselines under comparable token budgets, with continued gains as the budget scales up. These results suggest a scalable inference strategy for competitive code generation without any GT data.
  •  
  • ↗️
↗️

Imaging interface-controlled bulk oxygen spillover

✇Nature - Issue - nature.com science feeds
By: Weijue Wang · Hongbin Xu · Shuhui Liu · Xiaofeng Yang · Wei Liu · Yang-Gang Wang · Yanqiang Huang · Tao Zhang

Nature, Published online: 15 April 2026; doi:10.1038/s41586-026-10324-x

In situ microscopic single-particle imaging demonstrates the significance of rationally engineered metal–support interfaces for activating the oxygen in bulk catalyst, helping elucidate reaction pathways in catalytic conversions.
  •  
  • ↗️
↗️

Genetically encoded fluorescent reporters to visualize α-synuclein pathology in live brain

✇Cell
By: Li Zhang · Minhui Yu · Guoqing Chen · Siyuan Ge · Mengdi Wang · Xianying Zhang · Miao Zhao · Huating Gu · Meizhu Huang · Aixue Liu · Gengxin Ran · Zeyuan Liu · Tiepeng Liao · Qi Chen · Chenjian Miao · Yao Lu · Yibing Wang · Fengchao Wang · Zhihui Liu · Hongying Zhu · Qian Wu · Zhuan Zhou · Wei Xiong · Xiaoqun Wang · Peng Cao
The development of genetically encoded fluorescent reporters, along with their corresponding knock-in mouse lines for labeling α-Syn inclusions, enables diverse applications in studying the propagation and pathological effects of α-Syn inclusions in the live brain.
  •  
  • ↗️
↗️

DIAL: Decoupling Intent and Action via Latent World Modeling for End-to-End VLA

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yi Chen · Yuying Ge · Hui Zhou · Mingyu Ding · Yixiao Ge · Xihui Liu
arXiv:2603.29844v1 Announce Type: cross Abstract: The development of Vision-Language-Action (VLA) models has been significantly accelerated by pre-trained Vision-Language Models (VLMs). However, most existing end-to-end VLAs treat the VLM primarily as a multimodal encoder, directly mapping vision-language features to low-level actions. This paradigm underutilizes the VLM's potential in high-level decision making and introduces training instability, frequently degrading its rich semantic representations. To address these limitations, we introduce DIAL, a framework bridging high-level decision making and low-level motor execution through a differentiable latent intent bottleneck. Specifically, a VLM-based System-2 performs latent world modeling by synthesizing latent visual foresight within the VLM's native feature space; this foresight explicitly encodes intent and serves as the structural bottleneck. A lightweight System-1 policy then decodes this predicted intent together with the current observation into precise robot actions via latent inverse dynamics. To ensure optimization stability, we employ a two-stage training paradigm: a decoupled warmup phase where System-2 learns to predict latent futures while System-1 learns motor control under ground-truth future guidance within a unified feature space, followed by seamless end-to-end joint optimization. This enables action-aware gradients to refine the VLM backbone in a controlled manner, preserving pre-trained knowledge. Extensive experiments on the RoboCasa GR1 Tabletop benchmark show that DIAL establishes a new state-of-the-art, achieving superior performance with 10x fewer demonstrations than prior methods. Furthermore, by leveraging heterogeneous human demonstrations, DIAL learns physically grounded manipulation priors and exhibits robust zero-shot generalization to unseen objects and novel configurations during real-world deployment on a humanoid robot.
  •  
  • ↗️
↗️

The Yin and Yang of tertiary lymphoid structures in primary liver cancer

✇Omics in Hepatocellular
By: Hui Liu · Shi Chen · Muzi Cao · Lizhuang Shu · Mufan Ji · Jian Zhou · Jia Fan · Pengxiang Wang · Yunfan Sun

Cancer Lett. 2026 Mar 27;648:218461. doi: 10.1016/j.canlet.2026.218461. Online ahead of print.

ABSTRACT

Tertiary lymphoid structures (TLSs) have emerged as key regulators of anti-tumor immunity and biomarkers for immunotherapy response in liver cancer, including hepatocellular carcinoma (HCC), intrahepatic cholangiocarcinoma (iCCA), and combined hepatocellular-cholangiocarcinoma (cHCC-iCCA). Advances in single-cell and spatial multi-omics technologies have revealed unprecedented complexity in TLSs, challenging the traditional binary classification of TLSs as simply "good" or "bad". Their functional diversity appears to be shaped by spatiotemporal context, cellular composition, and maturation status. This review provides a comprehensive synthesis of TLSs in liver cancer, employing the Yin-Yang paradigm to navigate their functional dualism and prognostic contradictions through a detailed analysis of their identification, classification, and spatiotemporal interactions within the TME. Mechanistically, we elucidate how TLS functions are orchestrated by complex interactions between tumor cells, immune cell subsets, stromal components, and systemic factors. Within this framework, key metabolic drivers, notably ATP citrate lyase (ACLY), and signaling axes such as cGAS-STING/mTOR have emerged as pivotal regulators of TLS ontogeny. In addition, we evaluate current preclinical animal models and therapeutic strategies for clinical TLS induction. Furthermore, we have discussed the key unanswered questions in the field, including the three-dimensional architecture of TLSs and the mechanisms by which they establish durable immunological memory independent of the primary tumor. Clinically, TLSs exhibit great promise as prognostic and predictive biomarkers, particularly in the context of immune checkpoint blockade and locoregional therapies. Finally, we identify challenges in standardization, mechanistic understanding, and translational applications, providing directions for future research to harness TLSs for improving liver cancer outcomes.

PMID:41905709 | DOI:10.1016/j.canlet.2026.218461

  •  
  • ↗️
↗️

PhySe-RPO: Physics and Semantics Guided Relative Policy Optimization for Diffusion-Based Surgical Smoke Removal

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zining Fang · Chunhui Liu · Bin Xu · Ming Chen · Xiaowei Hu · Cheng Xue
arXiv:2603.22844v2 Announce Type: new Abstract: Surgical smoke severely degrades intraoperative video quality, obscuring anatomical structures and limiting surgical perception. Existing learning-based desmoking approaches rely on scarce paired supervision and deterministic restoration pipelines, making it difficult to perform exploration or reinforcement-driven refinement under real surgical conditions. We propose PhySe-RPO, a diffusion restoration framework optimized through Physics- and Semantics-Guided Relative Policy Optimization. The core idea is to transform deterministic restoration into a stochastic policy, enabling trajectory-level exploration and critic-free updates via group-relative optimization. A physics-guided reward imposes illumination and color consistency, while a visual-concept semantic reward learned from CLIP-based surgical concepts promotes smoke-free and anatomically coherent restoration. Together with a reference-free perceptual constraint, PhySe-RPO produces results that are physically consistent, semantically faithful, and clinically interpretable across synthetic and real robotic surgical datasets, providing a principled route to robust diffusion-based restoration under limited paired supervision.
  •  
  • ↗️
↗️

Three Creates All: You Only Sample 3 Steps

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yuren Cai · Guangyi Wang · Zongqing Li · Li Li · Zhihui Liu · Songzhi Su
arXiv:2603.22375v1 Announce Type: cross Abstract: Diffusion models deliver high-fidelity generation but remain slow at inference time due to many sequential network evaluations. We find that standard timestep conditioning becomes a key bottleneck for few-step sampling. Motivated by layer-dependent denoising dynamics, we propose Multi-layer Time Embedding Optimization (MTEO), which freeze the pretrained diffusion backbone and distill a small set of step-wise, layer-wise time embeddings from reference trajectories. MTEO is plug-and-play with existing ODE solvers, adds no inference-time overhead, and trains only a tiny fraction of parameters. Extensive experiments across diverse datasets and backbones show state-of-the-art performance in the few-step sampling and substantially narrow the gap between distillation-based and lightweight methods. Code will be available.
  •  
  • ↗️
↗️

Retrieval-Augmented Generation with Covariate Time Series

✇cs.AI, q-bio.NC updates on arXiv.org
By: Kenny Ye Liang · Zhongyi Pei · Huan Zhang · Yuhui Liu · Shaoxu Song · Jianmin Wang
arXiv:2603.04951v2 Announce Type: replace Abstract: While RAG has greatly enhanced LLMs, extending this paradigm to Time-Series Foundation Models (TSFMs) remains a challenge. This is exemplified in the Predictive Maintenance of the Pressure Regulating and Shut-Off Valve (PRSOV), a high-stakes industrial scenario characterized by (1) data scarcity, (2) short transient sequences, and (3) covariate coupled dynamics. Unfortunately, existing time-series RAG approaches predominantly rely on generated static vector embeddings and learnable context augmenters, which may fail to distinguish similar regimes in such scarce, transient, and covariate coupled scenarios. To address these limitations, we propose RAG4CTS, a regime-aware, training-free RAG framework for Covariate Time-Series. Specifically, we construct a hierarchal time-series native knowledge base to enable lossless storage and physics-informed retrieval of raw historical regimes. We design a two-stage bi-weighted retrieval mechanism that aligns historical trends through point-wise and multivariate similarities. For context augmentation, we introduce an agent-driven strategy to dynamically optimize context in a self-supervised manner. Extensive experiments on PRSOV demonstrate that our framework significantly outperforms state-of-the-art baselines in prediction accuracy. The proposed system is deployed in Apache IoTDB within China Southern Airlines. Since deployment, our method has successfully identified one PRSOV fault in two months with zero false alarm.
  •  
  • ↗️
↗️

Facile induction of immune tolerance by an interleukin-2–TGFβ surrogate agonist

✇Nature - Issue - nature.com science feeds
By: Qinli Sun · Alison K. Barrett · Masato Ogishi · Huiyun Lyu · Hua Jiang · Honghui Liu · Yang Zhao · Grayson E. Rodriguez · Pingdong Tao · Matthias Obenaus · Karsten D. Householder · Qizhi Tang · Tobias V. Lanz · K. Christopher Garcia

Nature, Published online: 11 March 2026; doi:10.1038/s41586-026-10208-0

A fusion protein designed to comprise IL-2 and a helminth-derived TGFβ mimic activates IL-2 and TGFβ signalling pathways in IL-2 receptor-expressing T cells and induces stable antigen-specific regulatory T cells in peripheral lymphoid organs.
  •  
  • ↗️
↗️

Agentic Critical Training

✇cs.AI, q-bio.NC updates on arXiv.org
By: Weize Liu · Minghui Liu · Sy-Tuyen Ho · Souradip Chakraborty · Xiyao Wang · Furong Huang
arXiv:2603.08706v1 Announce Type: new Abstract: Training large language models (LLMs) as autonomous agents often begins with imitation learning, but it only teaches agents what to do without understanding why: agents never contrast successful actions against suboptimal alternatives and thus lack awareness of action quality. Recent approaches attempt to address this by introducing self-reflection supervision derived from contrasts between expert and alternative actions. However, the training paradigm fundamentally remains imitation learning: the model imitates pre-constructed reflection text rather than learning to reason autonomously. We propose Agentic Critical Training (ACT), a reinforcement learning paradigm that trains agents to identify the better action among alternatives. By rewarding whether the model's judgment is correct, ACT drives the model to autonomously develop reasoning about action quality, producing genuine self-reflection rather than imitating it. Across three challenging agent benchmarks, ACT consistently improves agent performance when combined with different post-training methods. It achieves an average improvement of 5.07 points over imitation learning and 4.62 points over reinforcement learning. Compared to approaches that inject reflection capability through knowledge distillation, ACT also demonstrates clear advantages, yielding an average improvement of 2.42 points. Moreover, ACT enables strong out-of-distribution generalization on agentic benchmarks and improves performance on general reasoning benchmarks without any reasoning-specific training data, highlighting the value of our method. These results suggest that ACT is a promising path toward developing more reflective and capable LLM agents.
  •  
  • ↗️
↗️

GraphSkill: Documentation-Guided Hierarchical Retrieval-Augmented Coding for Complex Graph Reasoning

✇cs.AI, q-bio.NC updates on arXiv.org
By: Fali Wang · Chenglin Weng · Xianren Zhang · Siyuan Hong · Hui Liu · Suhang Wang
arXiv:2603.06620v1 Announce Type: cross Abstract: The growing demand for automated graph algorithm reasoning has attracted increasing attention in the large language model (LLM) community. Recent LLM-based graph reasoning methods typically decouple task descriptions from graph data, generate executable code augmented by retrieval from technical documentation, and refine the code through debugging. However, we identify two key limitations in existing approaches: (i) they treat technical documentation as flat text collections and ignore its hierarchical structure, leading to noisy retrieval that degrades code generation quality; and (ii) their debugging mechanisms focus primarily on runtime errors, yet ignore more critical logical errors. To address them, we propose {\method}, an \textit{agentic hierarchical retrieval-augmented coding framework} that exploits the document hierarchy through top-down traversal and early pruning, together with a \textit{self-debugging coding agent} that iteratively refines code using automatically generated small-scale test cases. To enable comprehensive evaluation of complex graph reasoning, we introduce a new dataset, {\dataset}, covering small-scale, large-scale, and composite graph reasoning tasks. Extensive experiments demonstrate that our method achieves higher task accuracy and lower inference cost compared to baselines\footnote{The code is available at \href{https://github.com/FairyFali/GraphSkill}{\textcolor{blue}{https://github.com/FairyFali/GraphSkill}}.}.
  •  
  • ↗️
↗️

MetaWorld-X: Hierarchical World Modeling via VLM-Orchestrated Experts for Humanoid Loco-Manipulation

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yutong Shen · Hangxu Liu · Penghui Liu · Jiashuo Luo · Yongkang Zhang · Rex Morvley · Chen Jiang · Jianwei Zhang · Lei Zhang
arXiv:2603.08572v1 Announce Type: cross Abstract: Learning natural, stable, and compositionally generalizable whole-body control policies for humanoid robots performing simultaneous locomotion and manipulation (loco-manipulation) remains a fundamental challenge in robotics. Existing reinforcement learning approaches typically rely on a single monolithic policy to acquire multiple skills, which often leads to cross-skill gradient interference and motion pattern conflicts in high-degree-of-freedom systems. As a result, generated behaviors frequently exhibit unnatural movements, limited stability, and poor generalization to complex task compositions. To address these limitations, we propose MetaWorld-X, a hierarchical world model framework for humanoid control. Guided by a divide-and-conquer principle, our method decomposes complex control problems into a set of specialized expert policies (Specialized Expert Policies, SEP). Each expert is trained under human motion priors through imitation-constrained reinforcement learning, introducing biomechanically consistent inductive biases that ensure natural and physically plausible motion generation. Building upon this foundation, we further develop an Intelligent Routing Mechanism (IRM) supervised by a Vision-Language Model (VLM), enabling semantic-driven expert composition. The VLM-guided router dynamically integrates expert policies according to high-level task semantics, facilitating compositional generalization and adaptive execution in multi-stage loco-manipulation tasks.
  •  
  • ↗️
↗️

Unbiased Dynamic Pruning for Efficient Group-Based Policy Optimization

✇cs.AI, q-bio.NC updates on arXiv.org
By: Haodong Zhu · Yangyang Ren · Yanjing Li · Mingbao Lin · Linlin Yang · Xuhui Liu · Xiantong Zhen · Haiguang Liu · Baochang Zhang
arXiv:2603.04135v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) effectively scales LLM reasoning but incurs prohibitive computational costs due to its extensive group-based sampling requirement. While recent selective data utilization methods can mitigate this overhead, they could induce estimation bias by altering the underlying sampling distribution, compromising theoretical rigor and convergence behavior. To address this limitation, we propose Dynamic Pruning Policy Optimization (DPPO), a framework that enables dynamic pruning while preserving unbiased gradient estimation through importance sampling-based correction. By incorporating mathematically derived rescaling factors, DPPO significantly accelerates GRPO training without altering the optimization objective of the full-batch baseline. Furthermore, to mitigate the data sparsity induced by pruning, we introduce Dense Prompt Packing, a window-based greedy strategy that maximizes valid token density and hardware utilization. Extensive experiments demonstrate that DPPO consistently accelerates training across diverse models and benchmarks. For instance, on Qwen3-4B trained on MATH, DPPO achieves 2.37$\times$ training speedup and outperforms GRPO by 3.36% in average accuracy across six mathematical reasoning benchmarks.
  •  
  • ↗️
There are no more articles
❌