Yuchi Wang, Rongyao Fang, Weihao Yu, Xilin Wei, Tiancheng Gu, Dingkang Yang, Hang Zhang, Dayiheng Liu 等 10 位作者
Beyond basic tool use and coding skills, effectively incorporating visual references into agentic generation is equally essential for applying AI agents to real-world productivity tasks. We study this crucial capability through webpage development, a practical and readily evaluable setting in which existing benchmarks remain largely idealized: they typically focus on reconstructing visual targets or generating webpages from textual instructions alone, overlooking the more common workflow of developing from visual examples. Specifically, we introduce RefCraft, a benchmark comprising 300 realistic multimodal webpage-development tasks that combine natural-language instructions with screenshots from one to five reference webpages. Agents must selectively interpret and utilize these references while rendering, visually inspecting, and iteratively refining their outputs. We evaluate the resulting open-ended artifacts using independently verifiable keypoints and complementary programmatic and VLM judges. Across nine frontier (M)LLMs, the strongest system achieves an overall score of only 52.12 out of 100, revealing that visual-reference-conditioned agentic generation remains a substantial challenge for current models in practical webpage-development settings.
Jiajun Liang, Yucheng Liao, Yukang Cao, Jiazhe Wei, Ken Li, Wende Tan, Jiankun Zhang, ZY Cui 等 15 位作者
Language remains an outlier in generative modeling: while images, video, and audio are increasingly modeled in continuous latent spaces, text generation still relies predominantly on discrete tokens. Existing continuous language models either inherit embedding spaces not designed for joint generation and decoding, or compress autoencoded latents to ease diffusion, sacrificing token-level fidelity. Instead of simplifying the representation to suit the generative model, we preserve a high-capacity, decodable text latent and design the diffusion model to learn its distribution directly. We introduce AURORA-LM, a continuous-latent diffusion language model that separates the construction of a decodable text representation from the modeling of its distribution. A Query-based Encoder-Decoder organizes text into a high-capacity, prefix-aligned latent sequence, and a Block-causal Diffusion Transformer learns its distribution through flow matching, generating blocks left to right while denoising positions within each block in parallel. Because such a latent is harder for diffusion to model, AURORA-LM restricts only the noisy-input pathway while retaining the full clean-latent prediction target, accommodating full-width latents without reducing decoder-facing capacity. We further calibrate the noise-level distribution to the latent width, and introduce self-trajectory consistency to bridge independently sampled training noise and iterative denoising at inference. AURORA-LM achieves the strongest performance among evaluated continuous and diffusion-based language models on OpenWebText free generation and XSum summarization. Scaling to 1B parameters with about 1500 EFLOPs of total compute yields further gains, surpassing a larger publicly released latent-diffusion language model under a matched evaluation protocol. All experiments are conducted on Ascend NPUs.
We propose VT-MUSE, a Multimodal Unified SEquential representation learning framework for visuotactilemanipulation. Existing approaches often encode visual and tactile observations independently before fusion, limiting their ability to capture fine-grained cross-modal dependencies. Moreover, most methods focus on observations at the current time step and overlook the temporal evolution of contact. VT-MUSE addresses both limitations through a two-stage representation learning framework. In Stage I, modality specific encoders are jointly adapted via cross-modal temporal alignment and masked-view consistency. In Stage II, a conditional variational latent model processes masked visual sequences together with full tactile histories. Auxiliary decoders reconstruct the masked recent visual observations and predict tactile depth changes, encouraging the latent representation to retain both global visual context and local contact dynamics. The learned representation is subsequently integrated into a lightweight Transformer policy through gated cross-attention. On the simulation benchmark, VT-MUSE outperforms the strongest baseline evaluated on all tasks by 11 percentage points and also achieves substantial improvements in real-world experiments.
Yujiao Shen, Jiahe Song, Haitian Li, Jingkang Yang, Ziwei Liu
Learning from human data offers a scalable path toward embodied intelligence, yet it requires models to accurately understand fine-grained human actions from egocentric observations. However, existing benchmarks remain limited in action atomicity, temporal precision, and hand-action association. We introduce EgoActionBench, a benchmark that represents continuous human manipulation as temporally localized atomic actions associated with the left hand, right hand, or both hands. EgoActionBench contains 1,407 episodes with 41,132 human-refined action annotations. To evaluate such dense predictions, we propose an evaluation protocol that retrieves temporally eligible candidates, selects a prediction by content agreement, and scores semantic fidelity and temporal overlap alongside action precision and recall, jointly capturing what happens, when it happens, and which hand performs it. We benchmark 20 baseline models and systems on EgoActionBench and further adapt two backbones, Qwen3-VL-4B and LLaVA-OneVision-2-8B, through supervised fine-tuning followed by reinforcement learning on automatically annotated training episodes. EgoAction improves EgoActionScore by 15.9 and 23.2 points on the two backbones, and both adapted models outperform all open-source baselines. Our experiments reveal substantial limitations of current models in action atomicity, temporal precision, and hand-action association, highlighting the gap between general video understanding and the action understanding required for embodied intelligence.
Humanoid controllers need the ability to yield to external forces while retaining the capacity to resume their original tasks. However, tracking objectives penalize the deviations needed for yielding, while relaxing tracking goals persistently can make task recovery harder. Existing approaches often rely on task-specific interaction command interfaces or constructed compliant motion data and reference trajectories, limiting the direct reuse of their compliance-training mechanisms across different task interfaces. We introduce CompliantBot, a compliance-training framework for motion tracking and velocity-command locomotion. It preserves the original task inputs and requires no preconstructed compliant data or target trajectories. A state-dependent interaction force field couples applied loads to the robot's motion, enabling local articulation and whole-body movement to change the forces experienced. A complementary force-magnitude reward encourages lower interaction loads, while task rewards are downweighted during loading and restored after release to coordinate yielding and task resumption. The trained policies use task inputs and proprioceptive history without explicit external-force measurements. Across both task interfaces, CompliantBot yields farther under constant pulls and experiences lower spring interaction loads than matched baselines, while resuming task tracking after force removal. CompliantBot achieves the highest task completion among the compared methods under stronger pulls. Power evaluations further show that CompliantBot has the lowest mean joint mechanical power among the compared methods. Real-robot demonstrations further illustrate compliant responses through arm motion, stepping, and body reorientation.
Medical Image Quality Assessment (IQA) serves as a critical safety gate for clinical AI, yet existing approaches rely on scalar metrics that fail to capture the descriptive, expert-like evaluation process central to clinical practice. We introduce MedQ-Bench, a comprehensive benchmark for language-based medical IQA evaluation with MLLMs, establishing a perception--description paradigm across 5 imaging modalities and over 40 quality attributes. The benchmark comprises two complementary tasks: MedQ-Perception probes low-level visual attribute discrimination via 2,600 expert-annotated perceptual queries; MedQ-Description covers both no-reference and comparison description sub-tasks with 708 expert-annotated samples, evaluated through a four-dimensional judging protocol. Comprehensive evaluation of 23 state-of-the-art MLLMs reveals that current models exhibit only preliminary and unstable capabilities, and highlights the urgent need for targeted optimization of MLLMs in medical IQA. Project & Dataset: https://github.com/liujiyaoFDU/MedQ-Bench
Fine-grained visual perception remains a bottleneck during post-training of multimodal large language models (MLLMs), as perceptual errors can constrain gains from reasoning-focused optimization. Although image-caption pre-training improves perception, its influence can weaken as subsequent stages change data mixtures and objectives. Continuing caption supervision during post-training is challenging because subjective, information-dense descriptions complicate verifiable reward design. We present PerceptRL, which strengthens perception at two complementary levels. Perception RL uses a multi-agent pipeline to extract verified errors from dense image captions and convert the corresponding visual facts into QA pairs with fixed answer labels and rule-based rewards. Chain QA links correlated errors, while multiple-choice QA combines unrelated errors. A specialized route targets high-error domains with tailored verification, and a domain-agnostic general route covers errors beyond these domains. Perception Agentic RL addresses fine-grained and dense cases unresolved by single-turn Perception RL through multi-turn inspection with visual tools. We observe coordinate drift even in models trained to use tools, where incorrect crops or annotations distort evidence and propagate errors. Coordinate Injection corrects spatial operations in cold-start trajectories, while a grounding-aware process reward supervises intermediate spatial fidelity alongside final-answer correctness. Training proceeds through shared cold-start SFT, single-turn Perception RL, and multi-turn Perception Agentic RL. Across seven benchmarks under a shared tool-use protocol, PerceptRL achieves 71.6% average accuracy, surpassing the base model with the same tools and the strongest evaluated frontier VLM by 15.7 and 5.2 percentage points, respectively.
Large language model agents have enabled software development through natural-language interaction, but extending this paradigm to end-to-end game development remains challenging. Building a playable game requires coordinating code, scenes, assets, animations, physics, and configurations, while allowing developers to validate their integrated behavior through interactive testing. We introduce VibeGame, a framework for creating complete 2D game projects from natural-language prompts and optional reference images. Its AI-native game engine represents project state as schema-validated structured text and provides frame-synchronous runtime control, enabling agents to inspect game states, execute actions, and verify behavior at their own pace. Built upon this interface, we design an Adversarial Agent Team of eight specialized agents to separate implementation from review, so that problems are found and fixed through multi-round loops. For each conducted and accepted project, we further introduce a training-free self-evolution mechanism to distill it into reusable skeletons, modules, and collaboration contracts for future development. We evaluate prompt-assets-to-game (PA2G), where agents are given an asset library, and prompt-to-game (P2G), where agents generate their own art. On a GameCraft-Bench subset, VibeGame in P2G consistently outperforms a range of agent harnesses in either P2G or PA2G with the same underlying model, including GPT-6.1-Sol.
Zhengyi Li, Yakai Wang, Jingwen Leng Shanghai Jiao Tong University, Kang Yang, Yu Yu, Jiaping Gui Shanghai Jiao Tong University, Yu Feng Shanghai Jiaotong University, Ning Liu 等 9 位作者
For Transformer models, cryptographically secure inference ensures that the client learns only the final output, while the server learns nothing about the client’s input. However, securely computing nonlinear layers remains a major efficiency bottleneck due to the substantial communication rounds and data transmission required. To address this issue, prior works reveal intermediate activations to the client, allowing nonlinear operations to be computed in plaintext. Although this approach significantly improves efficiency, exposing activations enables adversaries to extract model weights. To mitigate this risk, existing works employ a shuffling defense that reveals only randomly permuted activations to the client. In this work, we show that the shuffling defense is not as robust as previously claimed. We propose an attack that aligns differently shuffled activations to a common permutation and subsequently exploits them to extract model weights. Experiments on Pythia-70m and GPT-2 demonstrate that the proposed attack can align shuffled activations with mean squared errors ranging from 10^{-9} to 10^{-6}. With a query cost of approximately $1, the adversary can recover model weights with L1-norm differences ranging from 10^{-4} to 10^{-2} compared to the oracle weights.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Jinwei Zhang, Xucheng Liang University of Southern California, Yu Zhang, Ruijie Yu, Xiaokang Yang Shanghai Jiaotong University, Yaohui Jin Shanghai Jiaotong University, Yanyan Xu Shanghai Jiaotong University
Experimental protocols in organic synthesis specify not only the intended transformation but also an executable sequence of operations and conditions. While recent language models show strong chemistry knowledge, widely used evaluations remain less diagnostic of procedure-level decision making. In this setting, correctness requires consistent step ordering, feasibility under stated conditions, faithful entity-role grounding, and schema-parseable outputs that can be automatically validated against operational constraints. We present ChemReason-Bench, a human-validated benchmark for verifiable experimental procedure reasoning built on a structured representation with explicit placeholders and a unified schema, enabling automatic checks of many operational constraints. From 500 reactions, we instantiate 7306 benchmark tasks across six complementary formats: ordering, step validation, condition validation, schema-constrained completion, contrastive choice, and evidence-grounded rationalization. We further release a large-scale instantiation of the same templates for downstream adaptation studies, kept disjoint from the evaluation set. Using a unified evaluation protocol, we benchmark diverse open-source, proprietary, and domain-specific models and observe clear variation across the capability surface. We also report controlled adaptation experiments in the appendix, where supervised fine-tuning improves small models, preference optimization adds limited gains in our setting, and a gap remains to the strongest evaluated systems.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表