Tootfinder

Pointing to a Llama and Call it a Camel: On the Sycophancy of Multimodal Large Language Models
Renjie Pi, Kehao Miao, Li Peihang, Runtao Liu, Jiahui Gao, Jipeng Zhang, Xiaofang Zhou
https://arxiv.org/abs/2509.16149

Pointing to a Llama and Call it a Camel: On the Sycophancy of Multimodal Large Language Models
Multimodal large language models (MLLMs) have demonstrated extraordinary capabilities in conducting conversations based on image inputs. However, we observe that MLLMs exhibit a pronounced form of visual sycophantic behavior. While similar behavior has also been noted in text-based large language models (LLMs), it becomes significantly more prominent when MLLMs process image inputs. We refer to this phenomenon as the "sycophantic modality gap." To better understand this issue, we further analyz…

Source: Pylon, which uses AI to automate B2B customer service, raised $31M led by a16z and Bain Capital at a valuation in the hundreds of millions of dollars (Stephanie Palazzolo/The Information)
https://www.theinformation.com/articles/andreessen-…

Why Andreessen and Bain Backed a Self-Described ‘Zendesk Killer’
Automating customer service has been among the most popular applications of artificial intelligence models, and investors have pumped about $1 billion into six key startups developing them. Now, a seventh is throwing its hat into the ring.San Francisco-based startup Pylon has raised $31 million ...

U-MARVEL: Unveiling Key Factors for Universal Multimodal Retrieval via Embedding Learning with MLLMs
Xiaojie Li, Chu Li, Shi-Zhe Chen, Xi Chen
https://arxiv.org/abs/2507.14902

U-MARVEL: Unveiling Key Factors for Universal Multimodal Retrieval via Embedding Learning with MLLMs
Universal multimodal retrieval (UMR), which aims to address complex retrieval tasks where both queries and candidates span diverse modalities, has been significantly advanced by the emergence of MLLMs. While state-of-the-art MLLM-based methods in the literature predominantly adopt contrastive learning principles, they often differ in their specific training recipes. Despite their success, the mechanisms underlying their retrieval capabilities remain largely unexplored, potentially resulting in …

CCL-XCoT: An Efficient Cross-Lingual Knowledge Transfer Method for Mitigating Hallucination Generation
Weihua Zheng, Roy Ka-Wei Lee, Zhengyuan Liu, Kui Wu, AiTi Aw, Bowei Zou
https://arxiv.org/abs/2507.14239

CCL-XCoT: An Efficient Cross-Lingual Knowledge Transfer Method for Mitigating Hallucination Generation
Multilingual Large Language Models(MLLMs) demonstrate strong generalization across languages, yet they remain prone to hallucinations, especially in low-resource languages, due to training data imbalances. These hallucinations, which include inaccurate or fabricated outputs, are particularly problematic in domain-specific generation tasks (Chataigner et al., 2024). To address this challenge, we propose CCL-XCoT(Curriculum-based Contrastive Learning-based Cross-lingual Chain-of-Thought), a two-s…

EmoQ: Speech Emotion Recognition via Speech-Aware Q-Former and Large Language Model
Yiqing Yang, Man-Wai Mak
https://arxiv.org/abs/2509.15775 https://arxiv…

EmoQ: Speech Emotion Recognition via Speech-Aware Q-Former and Large Language Model
The performance of speech emotion recognition (SER) is limited by the insufficient emotion information in unimodal systems and the feature alignment difficulties in multimodal systems. Recently, multimodal large language models (MLLMs) have made progress in SER. However, MLLMs still suffer from hallucination and misclassification problems in complex emotion reasoning. To address these problems, we propose an MLLM-based framework called EmoQ, which generates query embeddings that fuse multimodal…

An Investigation Into Secondary School Students' Debugging Behaviour in Python
Laurie Gale, Sue Sentance
https://arxiv.org/abs/2508.14833 https://arxiv…

An Investigation Into Secondary School Students' Debugging Behaviour in Python
Background and context: Debugging is a common and often frustrating challenge for beginner programmers. Understanding students' debugging processes can help us identify the difficulties and misunderstandings they possess. However, we currently have limited knowledge of how secondary students debug in a text-based language, a medium through which millions of students will learn to program in the future. Objectives: In this paper, we investigate the debugging behaviour of K-12 students learning a…

Gorgeous: Revisiting the Data Layout for Disk-Resident High-Dimensional Vector Search
Peiqi Yin, Xiao Yan, Qihui Zhou, Hui Li, Xiaolu Li, Lin Zhang, Meiling Wang, Xin Yao, James Cheng
https://arxiv.org/abs/2508.15290

Gorgeous: Revisiting the Data Layout for Disk-Resident High-Dimensional Vector Search
Similarity-based vector search underpins many important applications, but a key challenge is processing massive vector datasets (e.g., in TBs). To reduce costs, some systems utilize SSDs as the primary data storage. They employ a proximity graph, which connects similar vectors to form a graph and is the state-of-the-art index for vector search. However, these systems are hindered by sub-optimal data layouts that fail to effectively utilize valuable memory space to reduce disk access and suffer …

NYC tech-scene sanguine about Mamdani
https://www.wired.com/story/tech…

Sarah Josepha Hale is called the godmother of Thanksgiving
because for 40 years she wrote and lobbied five presidents and congressmen to establish it as a national holiday.
Hale, who is probably best remembered as the author of “Mary Had a Little Lamb,”
also wrote the novel “Northwood; or Life North and South,”
which argued for the virtue of the North against the evil slave owners of the South.
One of the chapters in her book discussed the importance of Thanks…

The Africanization of Thanksgiving
Millions of families will come together today and celebrate their bounty by reflecting on God,…

Learning from Preferences and Mixed Demonstrations in General Settings
Jason R Brown, Carl Henrik Ek, Robert D Mullins
https://arxiv.org/abs/2508.14027 https://

Learning from Preferences and Mixed Demonstrations in General Settings
Reinforcement learning is a general method for learning in sequential settings, but it can often be difficult to specify a good reward function when the task is complex. In these cases, preference feedback or expert demonstrations can be used instead. However, existing approaches utilising both together are often ad-hoc, rely on domain-specific properties, or won't scale. We develop a new framing for learning from human data, \emph{reward-rational partial orderings over observations}, designed …