SonarLLM is a multimodal large language model that treats sonar as a native perceptual modality, combining a sonar‑specific encoder, physics‑aware feature enhancement, and reliability‑aware hierarchical fusion to align acoustic structure with optical semantics. The authors introduce SonarBench, a benchmark covering recognition, counting, visual question answering, and captioning across sonar‑only, optical‑only, and fusion settings, enabling controlled measurement of cross‑modal complementarity. SonarLLM achieves 72.0% macro accuracy on sonar‑only tasks and 68.7% under fusion, outperforming baselines by significant margins and demonstrating increasing fusion gains as optical visibility degrades.
By Cong Su, longxuan ma, Ling Dong, Guofeng Tang, Weijie Yin, Haohui Chen, Zhengtao Yu
The paper introduces Gated Activation Steering, an inference-time intervention that jointly mitigates hallucination and sycophancy in medical question answering. By learning separate steering directions from contrastive clinical pairs and applying them to specific attention heads, the method uses behavior‑specific gates to intervene only when needed. Experiments on EHR‑based clinical questions show that the 4‑billion‑parameter model with gated steering outperforms its unsteered counterpart and rivals larger models in resisting user pressure.
By Himanshu Tripathi, Subash Neupane, Shaswata Mitra, Sudip Mittal, Noorbakhsh Amiri Golilarz, Shahram Rahimi
The Transformer Accelerator (TFA) is a synthesizable, parameterizable INT8 memory‑to‑memory engine designed for transformer inference and machine translation. It features a one‑time‑multiplexed datapath that handles prompt processing and autoregressive generation, and implements key operations such as matrix multiplication, softmax, RMSNorm, and elementwise functions through eight 512‑bit macro‑op descriptors. In extensive verification, TFA achieved zero mismatches across 25 tests and 34 constrained‑random runs, matched floating‑point references on multiple translation tasks, and delivered a 20× speedup over a 22‑thread CPU while projecting significant energy reductions in larger designs.
By Shashank
arXiv:2608.24293v1 Announce Type: new
Abstract: Latent diffusion models have emerged as a dominant framework for high-fidelity image and video synthesis, operating in compact latent spaces with varia...
By Yeonkyeong Lee, Hyunsung Go, Jongmin Kim, Sewoong Lim, Donghoon Lee
RT-NeuS is a neuro‑symbolic framework for long‑form video question answering that retains the accuracy and formal guarantees of temporal‑logic‑guided methods while dramatically reducing inference latency. It achieves this by using coarse‑to‑fine adaptive sampling to focus on query‑relevant frames and batched proposition detection with KV‑cache reuse, enabling all propositions to be evaluated in a single forward pass. Experiments on LongVideoBench, Video‑MME, and MLVU show up to a 13× speed‑up on an NVIDIA H200 GPU while matching or surpassing prior neuro‑symbolic accuracy.
By Shawn Liang, Sahil Shah, Chengwei Zhou, S P Sharan, Harsh Goel, Arnab Sanyal, Sandeep Chinchali, Gourav Datta
arXiv:2608.23864v1 Announce Type: new
Abstract: Visual tokenizers increasingly inject semantic supervision into latent spaces to make downstream diffusion easier. Yet how these semantics should be or...
By Junqiu Yu, Pandeng Li, Yikai Wang, Jiaxing Zhao, Yujie Wei, Kaixun Jiang, Quanhao Li, Hongtao Yu, Zhihang Liu, Zhaohe Liao, Junjie Zhou, Yun Zheng, Yu Liu, Yanwei Fu
arXiv:2608.24207v1 Announce Type: new
Abstract: Semantic identifiers (SIDs) represent entities as hierarchical token sequences for generative retrieval and recommendation. Residual-quantization token...
By Yunxiao Luo, Siyuan Wang, Ben Chen, Chenyi Lei
LLM-as-judge is essential for evaluating open-ended text and steering post-training, yet improving the judge itself typically relies on expensive annotations, reward models, or distillation from stron...
Semantic identifiers (SIDs) represent entities as hierarchical token sequences for generative retrieval and recommendation. Residual-quantization tokenizers construct these sequences by selecting a co...
Large Language Models (LLMs) have shown strong capabilities in table reasoning, but their effectiveness degrades as tables grow in size and complexity due to irrelevant context and difficulty localizi...
The paper introduces Entropy-Valley (EV), a training‑free method for selecting target length in masked diffusion machine translation. EV evaluates candidate canvases by mean predictive entropy from all‑mask forward passes, choosing the length the model is best prepared to fill. Compared to a baseline that uses training‑corpus length statistics, EV recovers a substantial portion of the COMET‑22 gain across En→Zh, Zh→En, and En→De, and expert evaluation confirms adequacy improvements, especially for Zh→En.
By Yan Zhan, Mengkai Hou, Wanting Zhang, Zhijun Gao
The paper introduces a User Behavioral Densing Law that quantifies how the minimum sufficient tokenization capacity scales with data size in user representation learning. A pilot study on a billion‑scale Alipay dataset shows raw data scaling bottlenecks and the benefits of tokenization, while theoretical analysis and experiments reveal an approximately linear relationship between the logarithms of tokenization capacity and input data size. Using this law, the authors develop ALGN, an adaptive variable‑length tokenization method that outperforms existing baselines across diverse data sources and downstream tasks.
By Bin Dou, Junru Zhang, Zhaoyi Yuan, Wuliang Huang, Letian Gong, Baokun Wang, Huan Li, Yu Cheng, Weiqiang Wang
arXiv:2608.22926v1 Announce Type: new
Abstract: Gaze is increasingly used as an input signal for vision and multimodal models, yet no consensus exists on how to represent it across datasets. Raw trac...
By Virmarie Maquiling, Zhuojiang Cai, Enkelejda Kasneci
arXiv:2504.03337v2 Announce Type: replace
Abstract: Existing bias mitigation methods for Visual Question Answering (VQA), a typical Artificial intelligence application, endure two main limitations. F...
By Quanxing Xu, Ling Zhou, Xian Zhong, Feifei Zhang, Rubing Huang
arXiv:2608.22753v1 Announce Type: new
Abstract: Large language models (LLMs) excel at text understanding and generation, yet still struggle to reliably understand and apply externally provided proced...
By Bohan Yu, Pengfei Cao, Chen Han, Chenxi Zhou, Zhiheng Zhang, Zhiyang Xie, Wenhao Teng, Xiangwen Liao, Jun Zhao, Kang Liu
arXiv:2608.23265v1 Announce Type: new
Abstract: In long-term collaboration spanning multiple meetings, factual states such as decisions and risks are continually revised, overturned, and replaced. Ex...
By Dongsheng Chen, Tianyu Wang, Wenhui Que
arXiv:2608.21431v1 Announce Type: new
Abstract: Knowledge-based Visual Question Answering aims to answer questions about an image by integrating external knowledge with visual and textual information...
By Qiyou Liu, Yong Zhang, Jianjie Luo, Zhenguo Yang, Yi Yu
arXiv:2608.23330v1 Announce Type: new
Abstract: Video understanding requires intelligent agents to transcend mere recognition of visual facts and comprehend the underlying intents behind human action...
By Jiapeng Li, Ping Wei, Wenjuan Han, Song-Chun Zhu, Lifeng Fan
LuxIT is a monolingual instruction‑tuning dataset for Luxembourgish, created by synthesizing instruction‑answer pairs from native texts using the DeepSeek‑R1‑0528 model and a quality‑assurance LLM‑as‑judge process. The resulting 227,507 high‑quality pairs were used to fine‑tune 14 LLMs (≤15 B parameters), yielding an average accuracy increase of +5.37 percentage points on standardized Luxembourgish proficiency exams and improvements in macro‑averaged F1 on nine of the fourteen downstream NLP tasks. These findings demonstrate that synthetic monolingual data can effectively enhance LLM performance in low‑resource languages and reveal the complex relationship between exam performance and practical NLP gains.
By Julian Valline, Cedric Lothritz, Siwen Guo, Jordi Cabot
arXiv:2608.21385v1 Announce Type: cross
Abstract: Social media has become a central arena in which armed conflicts are contested, yet the pro-Israel and pro-Palestine communities on Telegram, whose b...
By Michail Zafeiropoulos, Despoina Antonakaki, Sotiris Ioannidis