Papers
Paste an arXiv link or drop a PDF. Reading agents add margin notes, figure guides, and a critical review
Ready to read
- MMEB-V3: Measuring the Performance Gaps of Omni-Modality Embedding ModelsMultimodal embedding models aim to map heterogeneous inputs, such as text, images, videos, and audio, into a shared semantic space. However, existing methods and benchmarks remain largely limited to partial modality coverage, making it difficult to systematically evaluate full-modality representation learning. In this work, we take a step toward the full-modality setting. We introduce MMEB-V3, a comprehensive benchmark that evaluates embeddings across text, image, video, audio, as well as agent-centric scenarios. To enable more fine-grained diagnosis, we further construct OmniSET (Omni-modality Semantic Equivalence Tuples), where semantically equivalent instances are represented across modalities, allowing us to disentangle semantic similarity from modality effects. Through experiments on MMEB-V3, we conduct a systematic analysis of full-modality embeddings and identify three key findings: (1) models often fail to retrieve the intended target modality; (2) cross-modal retrieval is highly asymmetric and dominated by query-modality bias; and (3) instruction-induced shifts are either insufficient or misaligned with the target modality, and therefore do not reliably improve retrieval. These results indicate that current multimodal embeddings are not yet capable of reliably enforcing modality constraints specified by instructions, and consequently fail to exhibit consistent modality-aware retrieval behavior. We hope MMEB-V3 provides a useful benchmark for understanding and diagnosing these limitations, and for guiding future research on full-modality embeddings.Haohang Huang Xuan Lu Mingyi Su Xuan Zhang, Ziyan Jiang Ping Nie, Kai Zou, Tomas Pfister, Wenhu Chen, Wei Zhang, Xiaoyu Shen, Rui Meng
- Mistral 7BWe introduce Mistral 7B, a 7–billion-parameter language model engineered for superior performance and efficiency. Mistral 7B outperforms the best open 13B model (Llama 2) across all evaluated benchmarks, and the best released 34B model (Llama 1) in reasoning, mathematics, and code generation. Our model leverages grouped-query attention (GQA) for faster inference, coupled with sliding window attention (SWA) to effectively handle sequences of arbitrary length with a reduced inference cost. We also provide a model fine-tuned to follow instructions, Mistral 7B – Instruct, that surpasses Llama 2 13B – chat model both on human and automated benchmarks. Our models are released under the Apache 2.0 license. Code: https://github.com/mistralai/mistral-src Webpage: https://mistral.ai/news/announcing-mistral-7b/Albert Q. Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford
- Repo-To-Skill: Distilling GitHub Repositories Into AI4AI SkillsAutonomous agents are beginning to carry out machine-learning (ML) research end to end. These agents combine a model backbone with a harness for planning, execution, memory, and verification, but this architecture still leaves domain-specific know-how outside the agent. We call this missing layer operational knowledge, the know-how that separates knowing a method from making it work. That knowledge is not absent from the field. It appears in repositories and papers, but in forms written for human readers and too large to load during a task. Once distilled into compact, verified skills, this knowledge can be reused across tasks rather than rediscovered during each run. We present DisCo, a skill-powered research agent that creates skills and uses them during research. Its distillation runs in two complementary forms: task-agnostic, condensing the field’s widely used repositories into reusable skills, and task-oriented, producing the skills a concrete task calls for. The former, applied across the open ecosystem, yields the AREX-Skill Library, with 5,000+ verified skills distilled from 1,000 widely used ML repositories and organized into 20 areas and 178 capability families. With the GPT-5.5 backbone, research harness, and downstream execution budget held fixed, the skill-equipped research agent scores 134.3% higher on MLE-bench, 34.4% higher on PaperBench, 9.2% higher on FrontierCS, and 14.0% higher on PassNet than the same agent without skills. These gains come from adding distilled operating context under that fixed setup.Jianlyu Chen1,2†‡, Yuyang Hu1,3†‡, Hongjin Qian1†, Jiawei Liu2†, Wenqing Wei1,2†‡, Xiaolong Chen2, Zhicheng Dou3∗, Chaozhuo Li1, Qiwei Ye1, Zheng Liu1,4∗
- BDH-CQ: In-Context Learning with Recurrent Latent ReasoningWe introduce BDH-CQ, a reasoning model that combines in-context learning with recurrent latent reasoning. Inputs presented at inference time continuously update the model’s recurrent memory; the model then solves a query through iterative computation in a high-dimensional latent space, without verbalizing its intermediate reasoning. We evaluate the model on the public ARC-AGI-1 evaluation set and use controlled ARC-like interventions to study what it learns from demonstrations, how consistently it applies an inferred transformation, and which concepts remain difficult. A 150M-parameter configuration reaches 29.5% pass@2 at a computed inference cost of $0.0007 per task—less than one-tenth of a cent. This operating point breaks through the previously reported ARC-AGI-1 cost–accuracy Pareto frontier, establishing a new state of the art in benchmark cost efficiency.Björn Engdahl, Adrian Kosowski, Jan Chorowski, Zuzanna Stamirowska, Przemysław Uznański, Junlin Jiang, Rohan Phadke, Remigiusz Kinas, Richard Zhong
- Douyin Multimodal Embedding Model Technical ReportMultimodal representation learning is a cornerstone of modern AI. By encoding multimodal queries and targets into vectors, it powers industrial applications such as search and recommendation, and increasingly underpins modern agents. Real-world platforms with complex modalities and massive-scale content, such as Douyin, Xiaohongshu, and YouTube, demand two capabilities simultaneously, efficiency under billion-scale indexing and fine-grained semantic discrimination for hard matching. Existing MLLM embedding models often struggle to jointly satisfy both requirements. Contrastive models are efficient but rely on pair-level supervision that is too coarse for fine-grained distinctions, while CoT-based models improve discrimination at the cost of explicit generation that is impractical to serve online. We present Douyin Multimodal Embedding (DME), a model that combines both strengths to meet the industrial demand for efficient and fine-grained representation. Specifically, DME is trained in two stages. Stage 1 performs large-scale contrastive pre-training that establishes a unified multimodal embedding space with broad modality and task coverage. Stage 2 supplements semantic sufficiency, the property that an embedding is grounded in retrieval-relevant evidence and preserves fine-grained counterpart-side semantics, through two complementary mechanisms. Evidence-Grounded Typed Latent Reasoning organizes retrieval evidence via hidden-space latent reasoning, and Cross-Conditional Reconstruction enforces counterpart-side semantics via cross-directional autoregressive reconstruction. Cross-Conditional Reconstruction is used only during training, and the latent tokens remain inside a single encoder forward pass and introduce only marginal query-side overhead. The generative supervision further makes DME embeddings information-complete, in that the input content can be recovered from them, which we quantify as an interpretable measure of semantic sufficiency and use to guide optimization in industrial settings. On MMEB-v2, DME achieves state-of-the-art results at comparable scales for both the 2B and 9B variants (74.8 and 78.4), with particularly strong performance on video and visual-document retrieval. In production, DME delivers a 2.92% relative improvement in overall score on Douyin’s in-house offline evaluation set, and has been deployed across a range of real-world Douyin scenarios such as generative search, image search, and AI search. Online A/B testing on Douyin search further confirms a 0.1% Lifetime (LT) gain.
- WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill EvolutionAgent skills package specialized knowledge and workflows into reusable resources that extend AI agent capabilities. Recent work automatically discovers such skills from agent experience, which enables agents to progressively adapt through interaction. However, the insights that guide skill development typically remain scattered across optimization histories, limiting their systematic reuse across iterations. We introduce WikiSkill, a framework that co-evolves agent skills with a persistent knowledge base (wiki). At a high level, WikiSkill separates raw execution experience, accumulated knowledge, and executable skills, while continuously consolidating experience into the wiki, which subsequent skill updates can build on. Across diverse benchmarks and models, WikiSkill consistently outperforms state-of-the-art skill-evolution methods and improves over no-skill baselines in most model-benchmark settings. We find that skill evolution complements model scaling: larger models generally benefit more from evolved skills, while smaller models with skills can outperform substantially larger models without them. We also find that evolved skills transfer effectively across models and model families, and skills evolved by other models can outperform self-evolved skills. Finally, our ablation studies confirm that persistent knowledge accumulation in the wiki is critical for effective skill evolution. These results demonstrate the benefits of systematically accumulating and refining agent experience for developing reusable and transferable skills.Liyan Tang, Cyrus Rashtchian, Chun-Sung Ferng, Andrew Tomkins, Da-Cheng Juan, Tu Vu
- Use of Digital Image Correlation Method to Measure Bio-Tissue DeformationTraditionally, strain gauge, extensometer, and reflection tracking markers have been used to measure the deformation of materials under loading. However, the anisotropy and inhomogeneity of most biological materials restricted the accessibility of the real strain field. Compared to the video extensometer, digital image correlation has the advantage of providing full-field displacement as well as strain information. In this study, a digital image correlation method (DIC) measurement system was employed for chicken breast bio-tissue deformation measurement. To increase the contrast for better correlation, a mixture of ground black pepper and white sesame was sprayed on the surface of samples. The first step was to correct the distorted image caused by the lens using the inverse distorted calibration method and then the influence of subset size and correlation criteria, sum of squared differences (SSD), and zero-normalized sum of squared differences (ZNSSD) were investigated experimentally for accurate measurement. Test results of the sample was translated along the horizontal direction from 0 mm to 3 mm, with an increment of 0.1 mm and the measurement result was compared, and the displacement set on the translation stage. The result shows that the error is less than 3%, and accurate measurement can be achieved with proper surface preparation, subset size, correlation criterion, and image correction. Detailed examination of the strain values show that the strain εx is proportional to the displacement of crosshead, but the strain εy indicates the viscoelastic behavior of tested bio-tissue. In addition, the tested bio-tissue's linear birefringence extracted by a Mueller matrix polarimetry is for comparison and is in good agreement. As noted above, the integration of the optical parameter measurement system and the digital image correlation method is proposed in this paper to analyze the relationship between the strain changes and optical parameters of biological tissue, and thus the relative optic-stress coefficient can be significantly characterized if Young's modulus of biological tissue is known.Terry Yuan-Fang Chen, Nhat Minh Dang, Zhao-Ying Wang, Liang-Wei Chang, Wei-Yu Ku, Yu-Lung Lo, Ming-Tzer Lin
- Restoring Voluntary Control of Locomotion after Paralyzing Spinal Cord InjuryHalf of human spinal cord injuries lead to chronic paralysis. Here, we introduce an electrochemical neuroprosthesis and a robotic postural interface designed to encourage supraspinally mediated movements in rats with paralyzing lesions. Despite the interruption of direct supraspinal pathways, the cortex regained the capacity to transform contextual information into task-specific commands to execute refined locomotion. This recovery relied on the extensive remodeling of cortical projections, including the formation of brainstem and intraspinal relays that restored qualitative control over electrochemically enabled lumbosacral circuitries. Automated treadmill-restricted training, which did not engage cortical neurons, failed to promote translesional plasticity and recovery. By encouraging active participation under functional states, our training paradigm triggered a cortex-dependent recovery that may improve function after similar injuries in humans.Rubia van den Brand, Janine Heutschi, Quentin Barraud, Jack DiGiovanna, Kay Bartholdi, Michèle Huerlimann, Lucia Friedli, Isabel Vollenweider, Eduardo Martin Moraud, Simone Duis, Nadia Dominici, Silvestro Micera, Pavel Musienko, Grégoire Courtine
- Attention Is All You NeedThe dominant sequence transduction models are based on complex recurrent or convolutional neural networks that include an encoder and a decoder. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 28.4 BLEU on the WMT 2014 English-to-German translation task, improving over the existing best results, including ensembles, by over 2 BLEU. On the WMT 2014 English-to-French translation task, our model establishes a new single-model state-of-the-art BLEU score of 41.8 after training for 3.5 days on eight GPUs, a small fraction of the training costs of the best models from the literature. We show that the Transformer generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, Illia Polosukhin
- Mixture-of-Agents Enhances Large Language Model CapabilitiesRecent advances in large language models (LLMs) demonstrate substantial capabilities in natural language understanding and generation tasks. With the growing number of LLMs, how to harness the collective expertise of multiple LLMs is an exciting open direction. Toward this goal, we propose a new approach that leverages the collective strengths of multiple LLMs through a Mixture-of-Agents (MoA) methodology. In our approach, we construct a layered MoA architecture wherein each layer comprises multiple LLM agents. Each agent takes all the outputs from agents in the previous layer as auxiliary information in generating its response. MoA models achieves state-of-art performance on AlpacaEval 2.0, MT-Bench and FLASK, surpassing GPT-4 Omni. For example, our MoA using only open-source LLMs is the leader of AlpacaEval 2.0 by a substantial gap, achieving a score of 65.1% compared to 57.5% by GPT-4 Omni.111Our code can be found in: https://github.com/togethercomputer/moa.Junlin Wang, Jue Wang, Ben Athiwaratkun, Ce Zhang, James Zou