1. TTLab at AlexandriaX-2026: A Fine-Tuned Surface Tagger for Arabic Machine-Translation Error-Span Detection and Classification

   http://arxiv.org/abs/2609.29633v1 · arxiv

   We present TTLab's submission to the AlexandriaX-2026 Subtask~3 on Arabic MT error span detection and classification. Our system frames the task as token-level classification over surface forms, preserving character offsets to ensure exact alignment with the evaluation metric. To handle severe label

2. CuriosAI Submission to the CASTLE Challenge at EgoVis 2026

   http://arxiv.org/abs/2605.27800v1 · arxiv

   CASTLE 2026 asks 185 multiple-choice questions over 600+ hours of synchronized multi-view egocentric video. We explore two approaches on top of a shared multimodal preprocessing layer, including per-person timelines, speaker-resolved transcripts, and multi-VLM caption ensembles. Approach A, SVA: Sea

3. Claim2Source at CheckThat! 2026: Improving Multilingual Scientific Claim-Source Retrieval with Verification-based Re-Ranking

   http://arxiv.org/abs/2607.04043v1 · arxiv

   Multilingual scientific claim-source retrieval aims to identify the scientific publication supporting a claim shared on social media. This task is challenging because claims often differ from source publications in terms of language, wording, and level of detail, which weakens the connection between

4. The Interspeech 2026 Audio Encoder Capability Challenge for Large Audio Language Models

   http://arxiv.org/abs/2603.22728v1 · arxiv

   This paper presents the Interspeech 2026 Audio Encoder Capability Challenge, a benchmark specifically designed to evaluate and advance the performance of pre-trained audio encoders as front-end modules for Large Audio Language Models (LALMs). While LALMs have shown remarkable understanding of comple

5. AutoMine Solution for AV2 2026 Scenario Mining Challenge

   http://arxiv.org/abs/2606.11874v1 · arxiv

   With the development of autonomous driving systems, mining high-value, safety-critical, and planning-relevant scenarios from large-scale driving logs has become essential for data-driven evaluation. In this paper, we propose AutoMine, a robust self-refining scenario mining method based on LLMs and V

6. Proceedings of the 2nd International Workshop on Low Carbon Computing (LOCO 2026)

   http://arxiv.org/abs/2608.02072v1 · arxiv

   This volume contains the proceedings of the 2nd International Workshop on Low Carbon Computing (LOCO 2026), held at Lancaster University, United Kingdom, on 10-11 September 2026. LOCO provides an interdisciplinary forum for research, practical tools, early-stage work, radical ideas, and critical per

7. Task-Specific Multimodal Question Answering Agents via Confidence Calibration and Incremental Reasoning for QANTA 2026

   http://arxiv.org/abs/2607.09623v1 · arxiv

   We present our submission to the QANTA 2026 shared challenge at the ICML 2026 Workshop on Efficient Multimodal Question Answering (EMM-QA). Quanta evaluates multimodal quizbowl systems that answer pyramid-style questions from incrementally revealed text and accompanying images while operating under

8. NTIRE 2026 Challenge on Video Saliency Prediction: Methods and Results

   http://arxiv.org/abs/2604.14816v1 · arxiv

   This paper presents an overview of the NTIRE 2026 Challenge on Video Saliency Prediction. The goal of the challenge participants was to develop automatic saliency map prediction methods for the provided video sequences. The novel dataset of 2,000 diverse videos with an open license was prepared for

9. BioSentinel at EXIST 2026: Soft-Label Optimization with XLM-RoBERTa for Sexism Intent Classification in Memes

   http://arxiv.org/abs/2607.24137v1 · arxiv

   This paper describes the BioSentinel team's participation in EXIST 2026 Task 2.2: Source Intention in Memes, part of the CLEF 2026 evaluation campaign. The task requires classifying the communicative intent behind memes as direct, judgemental, or no (non-sexist), under a Learning with Disagreement (

10. AlignAtt4LLM: Fast AlignAtt for Decoder-Only LLMs at IWSLT 2026 Simultaneous Speech Translation Task

    http://arxiv.org/abs/2606.03967v1 · arxiv

    We describe AlignAtt4LLM, an IWSLT 2026 simultaneous speech translation system for English to German, Italian, and Chinese. The system is a synchronous cascade: Qwen3-ASR with forced alignment produces an incrementally updated source transcript, and Gemma-4 E4B-it translates that prefix under an MT-

10 hasil · 1044 md