Tootfinder

ByteDance launches Seedream 4.0, an AI image model it claims can beat Google's viral "nano banana" model in prompt adherence, alignment, and aesthetics (Vincent Chow/South China Morning Post)
https://www.scmp.com/tech/big-tech/article…

ByteDance unveils new AI image model to rival Google DeepMind’s ‘Nano Banana’
ByteDance claims that Seedream 4.0 beat Gemini 2.5 Flash Image for image generation and editing on its internal evaluation benchmark.

Visual-TableQA: Open-Domain Benchmark for Reasoning over Table Images
Boammani Aser Lompo, Marc Haraoui
https://arxiv.org/abs/2509.07966 https://arxiv.org/…

Visual-TableQA: Open-Domain Benchmark for Reasoning over Table Images
Visual reasoning over structured data such as tables is a critical capability for modern vision-language models (VLMs), yet current benchmarks remain limited in scale, diversity, or reasoning depth, especially when it comes to rendered table images. Addressing this gap, we introduce Visual-TableQA, a large-scale, open-domain multimodal dataset specifically designed to evaluate and enhance visual reasoning over complex tabular data. Our generation pipeline is modular, scalable, and fully autonom…

Fast and Extensible Hybrid Embeddings with Micros
Sean Bocirnea, William J. Bowman
https://arxiv.org/abs/2509.07551 https://arxiv.org/pdf/2509.07551…

Fast and Extensible Hybrid Embeddings with Micros
Macro embedding is a popular approach to defining extensible shallow embeddings of object languages in Scheme like host languages. While macro embedding has even been shown to enable implementing extensible typed languages in systems like Racket, it comes at a cost: compile-time performance. In this paper, we revisit micros - syntax to intermediate representation (IR) transformers, rather than source syntax to source syntax transformers (macros). Micro embedding enables stopping at an IR, produ…

Large Language Model Hacking: Quantifying the Hidden Risks of Using LLMs for Text Annotation
Joachim Baumann, Paul R\"ottger, Aleksandra Urman, Albert Wendsj\"o, Flor Miriam Plaza-del-Arco, Johannes B. Gruber, Dirk Hovy
https://arxiv.org/abs/2509.08825

Large Language Model Hacking: Quantifying the Hidden Risks of Using LLMs for Text Annotation
Large language models (LLMs) are rapidly transforming social science research by enabling the automation of labor-intensive tasks like data annotation and text analysis. However, LLM outputs vary significantly depending on the implementation choices made by researchers (e.g., model selection, prompting strategy, or temperature settings). Such variation can introduce systematic biases and random errors, which propagate to downstream analyses and cause Type I, Type II, Type S, or Type M errors. W…

'Tennessee Three' legislator Justin Pearson launches primary challenge against longtime House Democrat (Bridget Bowman/NBC News)
https://www.nbcnews.com/politics/2026-election/tennessee-three-legislator-justin-pearson-launches-primary-challenge-l-rcna235918
http://www.memeorandum.com/251008/p48#a251008p48

Putting @… in my SPLASH-E talk brb.

Unlocking the Effectiveness of LoRA-FP for Seamless Transfer Implantation of Fingerprints in Downstream Models
Zhenhua Xu, Zhaokun Yan, Binhan Xu, Xin Tong, Haitao Xu, Yourong Chen, Meng Han
https://arxiv.org/abs/2509.00820

Unlocking the Effectiveness of LoRA-FP for Seamless Transfer Implantation of Fingerprints in Downstream Models
With the rapid advancement of large language models (LLMs), safeguarding intellectual property (IP) has become increasingly critical. To address the challenges of high costs and potential contamination in fingerprint integration, we propose LoRA-FP, a lightweight, plug-and-play framework that embeds backdoor fingerprints into LoRA adapters through constrained fine-tuning. This design enables seamless fingerprint transplantation via parameter fusion, eliminating the need for full-parameter updat…

EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing
Keming Wu, Sicong Jiang, Max Ku, Ping Nie, Minghao Liu, Wenhu Chen
https://arxiv.org/abs/2509.26346

EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing
Recently, we have witnessed great progress in image editing with natural language instructions. Several closed-source models like GPT-Image-1, Seedream, and Google-Nano-Banana have shown highly promising progress. However, the open-source models are still lagging. The main bottleneck is the lack of a reliable reward model to scale up high-quality synthetic training data. To address this critical bottleneck, we built \mname, trained with our new large-scale human preference dataset, meticulously…

Google says it is behind the viral "nano-banana" image model, launches it as Gemini 2.5 Flash Image with finer edit controls in Gemini app, Gemini API, more (Maxwell Zeff/TechCrunch)
https://techcrunch.com/2025/08/26/google-geminis-ai-image-m…

Google Gemini's AI image model gets a 'bananas' upgrade | TechCrunch
Google says that it's behind the anonymous AI image editor "nano-banana" that's been making waves on social media.

IFEvalCode: Controlled Code Generation
Jian Yang, Wei Zhang, Shukai Liu, Linzheng Chai, Yingshui Tan, Jiaheng Liu, Ge Zhang, Wangchunshu Zhou, Guanglin Niu, Zhoujun Li, Binyuan Hui, Junyang Lin
https://arxiv.org/abs/2507.22462

IFEvalCode: Controlled Code Generation
Code large language models (Code LLMs) have made significant progress in code generation by translating natural language descriptions into functional code; however, real-world applications often demand stricter adherence to detailed requirements such as coding style, line count, and structural constraints, beyond mere correctness. To address this, the paper introduces forward and backward constraints generation to improve the instruction-following capabilities of Code LLMs in controlled code ge…