💡 The paper discusses a new type of attack called multi-step trojan attacks that can bypass existing defenses in local language model agents. These agents can read and write files, call tools, and reuse workspace state across sessions, making them useful but also vulnerable to attacks. Attackers can embed malicious prompts within files or tool outputs, which the agent can then execute later, allowing them to gain persistent control over the system. The problem with existing defenses is that they inspect each step in isolation, so they can block a clear harmful action but fail to detect the earlier operation that planted the backdoor.

To address this threat, the authors introduce ClawTrojan, a benchmark designed to identify multi-step trojan attacks in local agentic harnesses. They tested ClawTrojan in a simulated workspace with a language model and found that it achieved a 95.5 percent attack success rate, while existing single-turn prompt-injection attacks had near-zero success rates on the same model.

To defend against these attacks, the authors propose DASGuard, a system that scans control-like text in sensitive local files, traces its origin, and removes control content that does not originate from a trusted source. The results show that DASGuard achieves strong dynamic defense by combining runtime attack blocking with sanitized commits to the workspace. Overall, the paper contributes to the development of new detection methods and defense strategies against multi-step trojan attacks in local language model agents.

💡 The paper presents AutoFigure-Edit, a system that generates editable scientific illustrations from text descriptions and reference images. The problem addressed is that existing automated systems for creating scientific illustrations are limited in their ability to be edited, styled, and refined efficiently. To solve this, AutoFigure-Edit combines long-context understanding, reference-guided styling, and native SVG editing to enable the creation of high-quality scientific illustrations that can be easily edited and refined. The system allows for flexible style adaptation through user-provided reference images, making it possible to generate illustrations in various styles. The results of the paper include the development of the AutoFigure-Edit system, which is made available through a website, a video demonstration, and an open-source codebase, facilitating further progress in the field of automated scientific illustration generation. The system enables efficient creation and refinement of high-quality scientific illustrations, making it a valuable tool for communicating complex scientific and technical concepts.

💡 The paper LongLive-RAG addresses the challenge of generating long videos using autoregressive video diffusion models. The problem with existing methods is that they use sliding-window attention, which can lead to error accumulation and identity drift over time. This is because once the active window accumulates appearance errors, subsequent generations can only condition on this degraded trajectory and drift further away. To overcome this limitation, the authors propose a retrieval-augmented generation framework called LongLive-RAG.

In this framework, previously generated latents are treated as a dynamic and searchable history. At each new block, LongLive-RAG uses a query embedding to retrieve relevant historical latents, allowing the generator to condition on non-local context instead of only the recent window. This retrieval step adds only a small overhead relative to generation and helps reduce error accumulation.

To make retrieval more discriminative, the authors introduce the Window Temporal Delta Loss, which suppresses redundant local similarity and encourages embeddings to capture meaningful temporal changes. The LongLive-RAG framework is general and can be used with multiple autoregressive backbones and generation lengths.

The experiments show that LongLive-RAG improves long video quality and achieves the best average VBench-Long rank. The authors claim that LongLive-RAG is the first method to formulate self-generated latent history as content-addressable retrieval memory, making it a significant contribution to the field of long video generation. The code for LongLive-RAG is available, making it possible for others to build upon and extend this work. Overall, the paper presents a novel approach to long video generation that addresses the limitations of existing methods and achieves state-of-the-art results.

💡 The paper addresses the challenge of creating high-quality scientific illustrations, which is a time-consuming and labor-intensive process. To tackle this problem, the authors introduce FigureBench, a large-scale benchmark consisting of 3300 high-quality scientific text-figure pairs, covering various text-to-illustration tasks from different sources. This benchmark provides a foundation for training and evaluating models that generate scientific illustrations from long-form scientific texts.

The authors also propose AutoFigure, an agentic framework that automatically generates high-quality scientific illustrations based on long-form scientific texts. AutoFigure engages in extensive thinking, recombination, and validation processes to produce a layout that is both structurally sound and aesthetically refined, resulting in a scientific illustration that achieves both structural completeness and aesthetic appeal.

The performance of AutoFigure is evaluated using the FigureBench benchmark, and the results demonstrate that AutoFigure consistently outperforms various baseline methods, producing publication-ready scientific illustrations. The authors release the code, dataset, and other resources to facilitate further research and development in this area.

Overall, the paper contributes to the development of automated tools for generating high-quality scientific illustrations, which can help alleviate the bottleneck in creating these illustrations and improve the communication of complex scientific and technical concepts. The introduction of FigureBench and AutoFigure provides a significant step forward in this direction, with the potential to benefit both academia and industry.

💡 The paper presents PaddleOCR-VL-1.6, an upgraded document parsing model that improves upon its predecessor PaddleOCR-VL-1.5. The problem with the previous model was that its errors were concentrated in under-optimized regions where the model was unstable, data coverage was sparse, or supervision was unreliable. To address this issue, the authors introduced a region-aware data optimization framework that identifies weak regions in the previous model and applies targeted enhancements to these regions, improving the reliability of supervision signals.

The method used in PaddleOCR-VL-1.6 involves a progressive post-training recipe based on curated data selection and reinforcement learning, which pushes the model's performance to a higher level through staged optimization. This approach allows for more efficient use of data and computational resources, rather than simply expanding the training corpus.

The results show that PaddleOCR-VL-1.6 achieves a state-of-the-art score of 96.33% on the OmniDocBench v1.6 benchmark, demonstrating strong competitiveness against top-tier visual language models. The paper provides a practical post-training recipe for the PaddleOCR-VL series, which can be used to further improve the performance of document parsing models. Overall, the contributions of the paper include a region-aware data optimization framework, a progressive post-training recipe, and a new state-of-the-art model for document parsing.