论文检索

Deep Learning · Everything Else

Dongzhi Jiang, Renrui Zhang, Ziyu Guo, Yanmin Wu, jiayi lei, Pengshuo Qiu, Pan Lu, Zehui Chen, Guanglu Song, Gao Peng 等

The advent of Large Language Models (LLMs) has paved the way for AI search engines, e.g., SearchGPT, showcasing a new paradigm in human-internet interaction. However, most current AI search engines are limited to text-only settings, neglecting the multimodal user queries and the text-image interleaved nature of website information. Recently, Large Multimodal Models (LMMs) have made impressive strides. Yet, whether they can function as AI search engines remains under-explored, leaving the potential of LMMs in multimodal search an open question. To this end, we first design a delicate pipeline, MMSearch-Engine, to empower any LMMs with multimodal search capabilities. On top of this, we introduce MMSearch, a comprehensive evaluation benchmark to assess the multimodal search performance of LMMs. The curated dataset contains 300 manually collected instances spanning 14 subfields, which involves no overlap with the current LMMs' training data, ensuring the correct answer can only be obtained within searching. By using MMSearch-Engine, the LMMs are evaluated by performing three individual tasks (requery, rerank, and summarization), and one challenging end-to-end task with a complete searching process. We conduct extensive experiments on closed-source and open-source LMMs. Among all tested models, GPT-4o with MMSearch-Engine achieves the best results, which surpasses the commercial product, Perplexity Pro, in the end-to-end task, demonstrating the effectiveness of our proposed pipeline. We further present error analysis to unveil current LMMs still struggle to fully grasp the multimodal search tasks, and conduct ablation study to indicate the potential of scaling test-time computation for AI search engine. We hope MMSearch may provide unique insights to guide the future development of multimodal AI search engine.

Deep Learning · Large Language Models

Zhiyong Wu, Zhenyu Wu, Fangzhi Xu, Yian Wang, Qiushi Sun, Chengyou Jia, Kanzhi Cheng, Zichen Ding, Liheng Chen, Paul Pu Liang 等

Existing efforts in building GUI agents heavily rely on the availability of robust commercial Vision-Language Models (VLMs) such as GPT-4o and GeminiProVision. Practitioners are often reluctant to use open-source VLMs due to their significant performance lag compared to their closed-source counterparts, particularly in GUI grounding and Out-Of-Distribution (OOD) scenarios. To facilitate future research in this area, we developed OS-Atlas—a foundational GUI action model that excels at GUI grounding and OOD agentic tasks through innovations in both data and modeling.We have invested significant engineering effort in developing an open-source toolkit for synthesizing GUI grounding data across multiple platforms, including Windows, Linux, MacOS, Android, and the web. Leveraging this toolkit, we are releasing the largest open-source cross-platform GUI grounding corpus to date, which contains over 13 million GUI elements. This dataset, combined with innovations in model training, provides a solid foundation for OS-Atlas to understand GUI screenshots and generalize to unseen interfaces.Through extensive evaluation across six benchmarks spanning three different platforms (mobile, desktop, and web), OS-Atlas demonstrates significant performance improvements over previous state-of-the-art models. Our evaluation also uncovers valuable insights into continuously improving and scaling the agentic capabilities of open-source VLMs.

Deep Learning · Large Language Models

Yongchao Chen, Harsh Jhamtani, Srinagesh Sharma, Chuchu Fan, Chi Wang

While a lot of recent research focuses on enhancing the textual reasoning capabilities of Large Language Models (LLMs) by optimizing the multi-agent framework or reasoning chains, several benchmark tasks can be solved with 100\% success through direct coding, which is more scalable and avoids the computational overhead associated with textual iterating and searching. Textual reasoning has inherent limitations in solving tasks with challenges in math, logics, optimization, and searching, which is unlikely to be solved by simply scaling up the model and data size. The recently released OpenAI GPT Code Interpreter and multi-agent frameworks such as AutoGen have demonstrated remarkable proficiency of integrating code generation and execution to solve complex tasks using LLMs. However, based on our experiments on 7 existing popular methods for steering code/text generation in both single- and multi-turn settings with 14 tasks and 6 types of LLMs (including the new O1-preview), currently there is no optimal method to correctly steer LLMs to write code when needed. We discover some interesting patterns on when models use code vs. textual reasoning with the evolution to task complexity and model sizes, which even result in an astonishingly inverse scaling behavior. We also discover that results from LLM written code are not always better than using textual reasoning, even if the task could be solved through code. To mitigate the above issues, we propose three methods to better steer LLM code/text generation and achieve a notable improvement. The costs of token lengths and runtime are thoroughly discussed for all the methods. We believe the problem of steering LLM code/text generation is critical for future research and has much space for further improvement. Project Page, Datasets, and Codes are available at https://yongchao98.github.io/CodeSteer/.

Dongping Chen, Ruoxi Chen, Shu Pu, Zhaoyi Liu, Yanru Wu, Caixi Chen, Benlin Liu, Yue Huang, Yao Wan, Pan Zhou 等

Many real-world user queries (e.g. *"How do to make egg fried rice?"*) could benefit from systems capable of generating responses with both textual steps with accompanying images, similar to a cookbook.Models designed to generate interleaved text and images face challenges in ensuring consistency within and across these modalities.To address these challenges, we present ISG, a comprehensive evaluation framework for interleaved text-and-image generation. ISG leverages a scene graph structure to capture relationships between text and image blocks, evaluating responses on four levels of granularity: holistic, structural, block-level, and image-specific. This multi-tiered evaluation allows for a nuanced assessment of consistency, coherence, and accuracy, and provides interpretable question-answer feedback.In conjunction with ISG, we introduce a benchmark, ISG-Bench, encompassing 1,150 samples across 8 categories and 21 subcategories. This benchmark dataset includes complex language-vision dependencies and golden answers to evaluate models effectively on vision-centric tasks such as style transfer, a challenging area for current models. Using ISG-Bench, we demonstrate that recent unified vision-language models perform poorly on generating interleaved content. While compositional approaches that combine separate language and image models show a 111% improvement over unified models at the holistic level, their performance remains suboptimal at both block and image levels.To facilitate future work, we develop ISG-Agent, a baseline agent employing a *"plan-execute-refine"* pipeline to invoke tools, achieving a 122% performance improvement.

Probabilistic Methods · Everything Else

Kaizheng Wang, Fabio Cuzzolin, Keivan Shariatmadar, David Moens, Hans Hallez

This paper presents an innovative approach, called credal wrapper, to formulating a credal set representation of model averaging for Bayesian neural networks (BNNs) and deep ensembles (DEs), capable of improving uncertainty estimation in classification tasks. Given a finite collection of single predictive distributions derived from BNNs or DEs, the proposed credal wrapper approach extracts an upper and a lower probability bound per class, acknowledging the epistemic uncertainty due to the availability of a limited amount of distributions. Such probability intervals over classes can be mapped on a convex set of probabilities (a credal set) from which, in turn, a unique prediction can be obtained using a transformation called intersection probability transformation. In this article, we conduct extensive experiments on several out-of-distribution (OOD) detection benchmarks, encompassing various dataset pairs (CIFAR10/100 vs SVHN/Tiny-ImageNet, CIFAR10 vs CIFAR10-C, CIFAR100 vs CIFAR100-C and ImageNet vs ImageNet-O) and using different network architectures (such as VGG16, ResNet-18/50, EfficientNet B2, and ViT Base). Compared to the BNN and DE baselines, the proposed credal wrapper method exhibits superior performance in uncertainty estimation and achieves a lower expected calibration error on corrupted data.

Yam Eitan, Yoav Gelberg, Guy Bar-Shalom, Fabrizio Frasca, Michael Bronstein, Haggai Maron

Topological deep learning (TDL) is a rapidly growing field that seeks to leverage topological structure in data and facilitate learning from data supported on topological objects, ranging from molecules to 3D shapes. Most TDL architectures can be unified under the framework of higher-order message-passing (HOMP), which generalizes graph message-passing to higher-order domains. In the first part of the paper, we explore HOMP's expressive power from a topological perspective, demonstrating the framework's inability to capture fundamental topological and metric invariants such as diameter, orientability, planarity, and homology. In addition, we demonstrate HOMP's limitations in fully leveraging lifting and pooling methods on graphs. To the best of our knowledge, this is the first work to study the expressivity of TDL from a topological perspective. In the second part of the paper, we develop two new classes of architectures -- multi-cellular networks (MCN) and scalable MCN (SMCN) -- which draw inspiration from expressive GNNs. MCN can reach full expressivity, but scaling it to large data objects can be computationally expansive. Designed as a more scalable alternative, SMCN still mitigates many of HOMP's expressivity limitations. Finally, we design new benchmarks for evaluating models based on their ability to learn topological properties of complexes. We then evaluate SMCN on these benchmarks as well as on real-world graph datasets, demonstrating improvements over both HOMP baselines and expressive graph methods, highlighting the value of expressively leveraging topological information.

Applications · Computer Vision

Donggoo Jung, Daehyun Kim, Tae Hyun Kim

Low-light image enhancement poses a significant challenge due to the limited information captured by image sensors in low-light environments. Despite recent improvements in deep learning models, the lack of paired training datasets remains a significant obstacle. Therefore, unsupervised methods have emerged as a promising solution. In this work, we focus on the strength of curve-adjustment-based approaches to tackle unsupervised methods. The majority of existing unsupervised curve-adjustment approaches iteratively estimate higher order curve parameters to enhance the exposure of images while efficiently preserving the details of the images. However, the convergence of the enhancement procedure cannot be guaranteed, leading to sensitivity to the number of iterations and limited performance. To address this problem, we consider the iterative curve-adjustment update process as a dynamic system and formulate it as a Neural Ordinary Differential Equations (NODE) for the first time, and this allows us to learn a continuous dynamics of the latent image. The strategy of utilizing NODE to leverage continuous dynamics in iterative methods enhances unsupervised learning and aids in achieving better convergence compared to discrete-space approaches. Consequently, we achieve state-of-the-art performance in unsupervised low-light image enhancement across various benchmark datasets.

Deep Learning · Large Language Models

Jiaxin Wen, Jian Guan, Hongning Wang, Wei Wu, Minlie Huang

Despite the remarkable success of large language models (LLMs) on traditional natural language processing tasks, their planning ability remains a critical bottleneck in tackling complex multi-step reasoning tasks. Existing approaches mainly rely on prompting or task-specific fine-tuning, often suffering from weak robustness and cross-task generalization. To address the limitation, we introduce CodePlan, a scalable paradigm that empowers LLMs to generate and follow code-form plans---pseudocode that outlines high-level, structured reasoning processes. By leveraging the structured and versatile nature of code, CodePlan effectively captures the rich semantics and control flows inherent to sophisticated reasoning. Importantly, CodePlan allows the automatic extraction of code-form plans from massive, wide-ranging text corpora without the need for curated, task-specific datasets. This enables it to scale up efficiently and improve reasoning capabilities across diverse scenarios. To train CodePlan, we construct a large-scale dataset of 2M examples that integrate code-form plans with standard prompt-response pairs from existing corpora. With minimal computation overhead during both training and inference, CodePlan achieves a 25.1\% relative improvement compared with directly generating responses, averaged across 13 challenging multi-step reasoning benchmarks, spanning mathematical reasoning, symbolic reasoning, instruction-following, multi-hop QA, and decision-making tasks. Further analysis reveals CodePlan's increasing performance gains on more complex reasoning tasks, as well as significant data efficiency thanks to its generalization ability.

Deep Learning · Large Language Models

Ziyan Jiang, Rui Meng, Xinyi Yang, Semih Yavuz, Yingbo Zhou, Wenhu Chen

Embedding models play a crucial role in a variety of downstream tasks, including semantic similarity, information retrieval, and clustering. While there has been a surge of interest in developing universal text embedding models that generalize across tasks (e.g., MTEB), progress in learning universal multimodal embedding models has been comparatively slow, despite their importance and practical applications. In this work, we explore the potential of building universal multimodal embeddings capable of handling a broad range of downstream tasks. Our contributions are twofold: (1) we propose MMEB (Massive Multimodal Embedding Benchmark), which covers four meta-tasks (classification, visual question answering, multimodal retrieval, and visual grounding) and 36 datasets, including 20 training datasets and 16 evaluation datasets spanning both in-distribution and out-of-distribution tasks, and (2) VLM2Vec (Vision-Language Model → Vector), a contrastive training framework that transforms any vision-language model into an embedding model through contrastive training on MMEB. Unlike previous models such as CLIP and BLIP, which encode text and images independently without task-specific guidance, VLM2Vec can process any combination of images and text while incorporating task instructions to generate a fixed-dimensional vector. We develop a series of VLM2Vec models based on state-of-the-art VLMs, including Phi-3.5-V, LLaVA-1.6, and Qwen2-VL, and evaluate them on MMEB’s benchmark. With LoRA tuning, VLM2Vec achieves a 10% to 20% improvement over existing multimodal embedding models on MMEB’s evaluation sets. Our findings reveal that VLMs are surprisingly strong embedding models.

Miscellaneous Aspects of Machine Learning · Causality

Mathieu Chevalley, Patrick Schwab, Arash Mehrjou

Targeted and uniform interventions to a system are crucial for unveiling causal relationships. While several methods have been developed to leverage interventional data for causal structure learning, their practical application in real-world scenarios often remains challenging. Recent benchmark studies have highlighted these difficulties, even when large numbers of single-variable intervention samples are available. In this work, we demonstrate, both theoretically and empirically, that such datasets contain a wealth of causal information that can be effectively extracted under realistic assumptions about the data distribution. More specifically, we introduce a novel variant of interventional faithfulness, which relies on comparisons between the marginal distributions of each variable across observational and interventional settings, and we introduce a score on causal orders. Under this assumption, we are able to prove strong theoretical guarantees on the optimum of our score that also hold for large-scale settings. To empirically verify our theory, we introduce Intersort, an algorithm designed to infer the causal order from datasets containing large numbers of single-variable interventions by approximately optimizing our score. Intersort outperforms baselines (GIES, DCDI, PC and EASE) on almost all simulated data settings replicating common benchmarks in the field. Our proposed novel approach to modeling interventional datasets thus offers a promising avenue for advancing causal inference, highlighting significant potential for further enhancements under realistic assumptions.

Deep Learning · Large Language Models

Jeonghoon Shim, Gyuhyeon Seo, Cheongsu Lim, Yohan Jo

Tool-Augmented Language Models (TALMs) leverage external APIs to answer user queries across various domains. However, existing benchmark datasets for TALM research often feature simplistic dialogues that do not reflect real-world scenarios, such as the need for models to ask clarifying questions or proactively call additional APIs when essential information is missing. To address these limitations, we construct and release ToolDial, a dataset comprising 11,111 multi-turn dialogues, with an average of 8.95 turns per dialogue, based on APIs from RapidAPI. ToolDial has two key characteristics. First, the dialogues incorporate 16 user and system actions (e.g., request, clarify, fail inform) to capture the rich dynamics of real-world interactions. Second, we simulate dialogues where the system requests necessary information from the user based on API documentation and seeks additional APIs if the user fails to provide the required information. To facilitate this process, we introduce a method for generating an API graph that represents input and output compatibility between APIs. Using ToolDial, we evaluate a suite of language models on their ability to predict correct actions and extract input parameter values for API calls from the dialogue history. Modern language models achieve accuracy scores below 70\%, indicating substantial room for improvement. We provide a detailed analysis of the areas where these models fall short.

Probabilistic Methods · Bayesian Models and Methods

Yogesh Verma, Ayush Bharti, Vikas Garg

Simulation-based inference (SBI) methods typically require fully observed data to infer parameters of models with intractable likelihood functions. However, datasets often contain missing values due to incomplete observations, data corruptions (common in astrophysics), or instrument limitations (e.g., in high-energy physics applications). In such scenarios, missing data must be imputed before applying any SBI method. We formalize the problem of missing data in SBI and demonstrate that naive imputation methods can introduce bias in the estimation of SBI posterior. We also introduce a novel amortized method that addresses this issue by jointly learning the imputation model and the inference network within a neural posterior estimation (NPE) framework. Extensive empirical results on SBI benchmarks show that our approach provides robust inference outcomes compared to standard baselines for varying levels of missing data. Moreover, we demonstrate the merits of our imputation model on two real-world bioactivity datasets (Adrenergic and Kinase assays). Code is available at https://github.com/Aalto-QuML/RISE.

Deep Learning · Robustness

Priyank Pathak, Shyam Marjit, Shruti Vyas, Yogesh S Rawat

Visual-language foundation Models (FMs) exhibit remarkable zero-shot generalization across diverse tasks, largely attributed to extensive pre-training on largescale datasets. However, their robustness on low-resolution/pixelated (LR) images, a common challenge in real-world scenarios, remains underexplored. We introduce LR0.FM, a comprehensive benchmark evaluating the impact of low resolution on the zero-shot classification performance of 10 FM(s) across 66 backbones and 15 datasets. We propose a novel metric, Weighted Aggregated Robustness, to address the limitations of existing metrics and better evaluate model performance across resolutions and datasets. Our key findings show that: (i) model size positively correlates with robustness to resolution degradation, (ii) pre-training dataset quality is more important than its size, and (iii) fine-tuned and higher resolution models are less robust against LR. Our analysis further reveals that the model makes semantically reasonable predictions at LR, and the lack of fine-grained details in input adversely impacts the model’s initial layers more than the deeper layers. We use these insights and introduce a simple strategy, LR-TK0, to enhance the robustness of models without compromising their pre-trained weights. We demonstrate the effectiveness of LR-TK0 for robustness against low-resolution across several datasets and its generalization capability across backbones and other approaches. Code is available at this : https://github.com/shyammarjit/LR0.FM

Yanbiao Ma, Wei Dai, Jiayi Chen

In object detection, the number of instances is commonly used to determine whether a dataset follows a long-tailed distribution, implicitly assuming that the model will perform poorly on categories with fewer instances. This assumption has led to extensive research on category bias in datasets with imbalanced instance distributions. However, even in datasets with relatively balanced instance counts, models still exhibit bias toward certain categories, indicating that instance count alone cannot explain this phenomenon. In this work, we first introduce the concept and measurement of category informativeness. We observe a significant negative correlation between a category’s informativeness and its accuracy, suggesting that informativeness more accurately reflects the learning difficulty of a category. Based on this observation, we propose the Informativeness-Guided Angular Margin Loss (IGAM Loss), which dynamically adjusts the decision space of categories according to their informativeness, thereby mitigating category bias in long-tailed datasets. IGAM Loss not only achieves superior performance on long-tailed benchmark datasets such as LVIS v1.0 and COCO-LT but also demonstrates significant improvements for underrepresented categories in non-long-tailed datasets like Pascal VOC. Extensive experiments confirm the potential of category informativeness as a tool and the generalizability of our proposed method.

Applications · Everything Else

Haotian Xia, Zhengbang Yang, Junbo Zou, Rhys Tracy, Yuqing Wang, Chi Lu, Christopher Lai, Yanjun He, Xun Shao, Zhuoqing Xie 等

Multimodal Large Language Models (MLLMs) are advancing the ability to reason about complex sports scenarios by integrating textual and visual information. To comprehensively evaluate their capabilities, we introduce SPORTU, a benchmark designed to assess MLLMs across multi-level sports reasoning tasks. SPORTU comprises two key components: SPORTU-text, featuring 900 multiple-choice questions with human-annotated explanations for rule comprehension and strategy understanding. This component focuses on testing models' ability to reason about sports solely through question-answering (QA), without requiring visual inputs; SPORTU-video, consisting of 1,701 slow-motion video clips across 7 different sports and 12,048 QA pairs, designed to assess multi-level reasoning, from simple sports recognition to complex tasks like foul detection and rule application. We evaluated four prevalent LLMs mainly utilizing few-shot learning paradigms supplemented by chain-of-thought (CoT) prompting on the SPORTU-text part. GPT-4o achieves the highest accuracy of 71\%, but still falls short of human-level performance, highlighting room for improvement in rule comprehension and reasoning. The evaluation for the SPORTU-video part includes 6 proprietary and 8 open-source MLLMs. Experiments show that models fall short on hard tasks that require deep reasoning and rule-based understanding. GPT-4o performs the best with only 57.8\% accuracy on the hard task, showing large room for improvement. We hope that SPORTU will serve as a critical step toward evaluating models' capabilities in sports understanding and reasoning. The dataset is available at [https://github.com/chili-lab/SPORTU](https://github.com/chili-lab/SPORTU).

Zhuoxiao Chen, Junjie Meng, Mahsa Baktashmotlagh, Yonggang Zhang, Zi Huang, Yadan Luo

LiDAR-based 3D object detection is crucial for various applications but often experiences performance degradation in real-world deployments due to domain shifts. While most studies focus on cross-dataset shifts, such as changes in environments and object geometries, practical corruptions from sensor variations and weather conditions remain underexplored. In this work, we propose a novel online test-time adaptation framework for 3D detectors that effectively tackles these shifts, including a challenging $\textit{cross-corruption}$ scenario where cross-dataset shifts and corruptions co-occur. By leveraging long-term knowledge from previous test batches, our approach mitigates catastrophic forgetting and adapts effectively to diverse shifts. Specifically, we propose a Model Synergy (MOS) strategy that dynamically selects historical checkpoints with diverse knowledge and assembles them to best accommodate the current test batch. This assembly is directed by our proposed Synergy Weights (SW), which perform a weighted averaging of the selected checkpoints, minimizing redundancy in the composite model. The SWs are computed by evaluating the similarity of predicted bounding boxes on the test data and the independence of features between checkpoint pairs in the model bank. To maintain an efficient and informative model bank, we discard checkpoints with the lowest average SW scores, replacing them with newly updated models. Our method was rigorously tested against existing test-time adaptation strategies across three datasets and eight types of corruptions, demonstrating superior adaptability to dynamic scenes and conditions. Notably, it achieved a 67.3% improvement in a challenging cross-corruption scenario, offering a more comprehensive benchmark for adaptation. Source code: https://github.com/zhuoxiao-chen/MOS.

Applications · Language, Speech and Dialog

Chenjia Bai, Yang Zhang, Shuang Qiu, Qiaosheng Zhang, Kang Xu, Xuelong Li

Reinforcement Learning from Human Feedback (RLHF) has shown great potential in fine-tuning Large Language Models (LLMs) to align with human preferences. Existing methods perform preference alignment from a fixed dataset, which can be limited in data coverage and the resulting reward model is hard to generalize in out-of-distribution responses. Thus, online RLHF is more desirable to empower the LLM to explore outside the support of the initial dataset by iteratively collecting the prompt-response pairs. In this paper, we study the fundamental problem in online RLHF, i.e., how to explore for LLM. We give a theoretical motivation in linear reward assumption to show that an optimistic reward with an upper confidence bound (UCB) term leads to a provably efficient RLHF policy. Then, we reformulate our objective to direct preference optimization with an exploration term, where the UCB-term can be converted to a count-based exploration bonus. We further propose a practical algorithm, named Count-based Online Preference Optimization (COPO), which leverages a simple coin-flip counting module to estimate the pseudo-count of a prompt-response pair in previously collected data. COPO encourages LLMs to balance exploration and preference optimization in an iterative manner, which enlarges the exploration space and the entire data coverage of iterative LLM policies. We conduct online RLHF experiments on Zephyr and Llama-3 models. The results on instruction-following and standard academic benchmarks show that COPO significantly increases performance.

Mintong Kang, Bo Li

As large language models (LLMs) become increasingly prevalent across various applications, it is critical to establish safety guardrails to moderate input/output content of LLMs and ensure compliance with safety policies. Existing guardrail models, such as OpenAI Mod and LlamaGuard, treat various safety categories (e.g., self-harm, self-harm/instructions) independently and fail to explicitly capture the intercorrelations among them. This has led to limitations such as ineffectiveness due to inadequate training on long-tail data from correlated safety categories, susceptibility to jailbreaking attacks, and inflexibility regarding new safety categories.To address these limitations, we propose $R^2$-Guard, a robust reasoning enabled LLM guardrail via knowledge-enhanced logical reasoning. Specifically, $R^2$-Guard comprises two parts: data-driven guardrail models and reasoning components. The data-driven guardrail models provide unsafety probabilities of moderated content on different safety categories.We then encode safety knowledge among different categories as first-order logical rules and embed them into a probabilistic graphic model (PGM) based reasoning component. The unsafety probabilities of different categories from data-driven guardrail models are sent to the reasoning component for final inference. We employ two types of PGMs: Markov logic networks (MLNs) and probabilistic circuits (PCs), and optimize PCs to achieve precision-efficiency balance via improved graph structure. We also propose different methods to optimize the weights of knowledge. To further perform stress tests for guardrail models, we employ a pairwise construction method to construct a new safety benchmark TwinSafety, which features principled categories and presents new challenges for moderation. We show that $R^2$-Guard is effective even given unrepresentative categories or challenging jailbreaking prompts. We demonstrate the effectiveness of $R^2$-Guard by comparisons with eight strong guardrail models on six standard moderation datasets, and demonstrate the robustness of $R^2$-Guard against four SOTA jailbreaking attacks. $R^2$-Guard significantly surpasses SOTA method LlamaGuard by 12.6% on standard moderation datasets and by 59.9% against jailbreaking attacks.We further reveal that $R^2$-Guard can effectively adapt to safety category updates by simply editing the PGM reasoning graph.

Yang Tian, Sizhe Yang, Jia Zeng, Ping Wang, Dahua Lin, Hao Dong, Jiangmiao Pang

Current efforts to learn scalable policies in robotic manipulation primarily fall into two categories: one focuses on "action," which involves behavior cloning from extensive collections of robotic data, while the other emphasizes "vision," enhancing model generalization by pre-training representations or generative models, also referred to as world models, using large-scale visual datasets. This paper presents an end-to-end paradigm that predicts actions using inverse dynamics models conditioned on the robot's forecasted visual states, named Predictive Inverse Dynamics Models (PIDM). By closing the loop between vision and action, the end-to-end PIDM can be a better scalable action learner. In practice, we use Transformers to process both visual states and actions, naming the model Seer. It is initially pre-trained on large-scale robotic datasets, such as DROID, and can be adapted to real-world scenarios with a little fine-tuning data. Thanks to large-scale, end-to-end training and the continuous synergy between vision and action at each execution step, Seer significantly outperforms state-of-the-art methods across both simulation and real-world experiments. It achieves improvements of 13% on the LIBERO-LONG benchmark, 22% on CALVIN ABC-D, and 43% in real-world tasks. Notably, it demonstrates superior generalization for novel objects, lighting conditions, and environments under high-intensity disturbances. Code and models will be publicly available.

Gregor Bachmann, Sotiris Anagnostidis, Albert Pumarola, Markos Georgopoulos, Artsiom Sanakoyeu, Yuming Du, Edgar Schoenfeld, Ali Thabet, Jonas Kohler

The performance of large language models (LLMs) is closely linked to their underlying size, leading to ever-growing networks and hence slower inference. Speculative decoding has been proposed as a technique to accelerate autoregressive generation, leveraging a fast draft model to propose candidate tokens, which are then verified in parallel based on their likelihood under the target model. While this approach guarantees to reproduce the target output, it incurs a substantial penalty: many high-quality draft tokens are rejected, even when they represent objectively valid continuations. Indeed, we show that even powerful draft models such as GPT-4o, as well as human text cannot achieve high acceptance rates under the standard verification scheme. This severely limits the speedup potential of current speculative decoding methods, as an early rejection becomes overwhelmingly likely when solely relying on alignment of draft and target.We thus ask the following question: Can we adapt verification to recognize correct, but non-aligned replies? To this end, we draw inspiration from the LLM-as-a-judge framework, which demonstrated that LLMs are able to rate answers in a versatile way. We carefully design a dataset coined TokenCourt to elicit the same capability in the target model by training a compact module on top of the embeddings to produce ``judgements" of the current continuation. We showcase our strategy on the Llama-3.1 family, where our 8B/405B-Judge achieves a speedup of $9\times$ over Llama-405B, while maintaining its quality on a large range of benchmarks. These benefits remain present even in optimized inference frameworks, where our method reaches up to $141$ tokens/s for 8B/70B-Judge and $129$ tokens/s for 8B/405B on $2$ and $8$ H100s respectively.