1. LLM-INSTRUCT at UZH Shared Task 2026: Constraint-Aware Retrieval and Selective Debate for Paragraph-Level Argument Mining

   http://arxiv.org/abs/2607.20430v1 · arxiv

   We present LLM-INSTRUCT, the winning system for the UZH Shared Task at ArgMining 2026 on paragraph-level argument mining in UN and UNESCO resolutions. The task requires paragraph-type classification, prediction of a subset of 141 official tags, and directed relation prediction under a strict JSON sc

2. Learning Speaker Identity Beyond Language and Modality Constraints: Insights from the POLY-SIM 2026 Challenge

   http://arxiv.org/abs/2607.13669v1 · arxiv

   Multimodal speaker identification systems typically assume the availability of complete and homogeneous audio-visual modalities during both training and testing, and assume each speaker only speaks a single language. However, in real-world applications, such assumptions often do not hold. Visual or

3. In Memoriam: Igal Talmi (1925-2026)

   http://arxiv.org/abs/2607.00787v1 · arxiv

   A brief obituary of Igal Talmi (1925-2026) focusing on his scientific heritage. Published in Nuclear Physics News 36 (2026) 39-40.

4. International AI Safety Report 2026

   http://arxiv.org/abs/2602.21012v1 · arxiv

   The International AI Safety Report 2026 synthesises the current scientific evidence on the capabilities, emerging risks, and safety of general-purpose AI systems. The report series was mandated by the nations attending the AI Safety Summit in Bletchley, UK. 29 nations, the UN, the OECD, and the EU e

5. NAVER LABS Europe Submission to the Instruction-following 2026 Short Track

   http://arxiv.org/abs/2607.01960v1 · arxiv

   In this paper, we describe NAVER LABS Europe's submission to the instruction-following speech processing short track at IWSLT 2026. We participate again in the constrained setting, developing systems capable of jointly performing ASR, ST, and SQA from English speech into Chinese, Italian, and German

6. A Response to paper Critical Evaluation of Studies Alleging Evidence for Technosignatures in the POSS1-E Photographic Plates by Watters et al. (2026)

   http://arxiv.org/abs/2602.15171v2 · arxiv

   We respond to the critique by Watters et al. (2026) of the statistical analyses in Villarroel et al. (2025) and Bruehl & Villarroel (2025). We argue that the critique conflates object-level validation with ensemble-level statistical inference and relies on a reduced, heterogeneously filtered subset

7. CorPipe at CRAC 2026: Empty Nodes and Cross-Lingual Transfer in Multilingual Coreference Resolution

   http://arxiv.org/abs/2605.30133v2 · arxiv

   We introduce CorPipe 26, our winning submission to the CRAC 2026 Shared Task on Multilingual Coreference Resolution. The fifth edition of this shared task focuses mainly on the comparison of generative LLMs and specialized systems; additionally, 5 more datasets and 2 new languages are introduced. Co

8. MKJ at SemEval-2026 Task 9: A Comparative Study of Generalist, Specialist, and Ensemble Strategies for Multilingual Polarization

   http://arxiv.org/abs/2604.21370v2 · arxiv

   We present a systematic study of multilingual polarization detection across 22 languages for SemEval-2026 Task 9 (Subtask 1), contrasting multilingual generalists with language-specific specialists and hybrid ensembles. While a standard generalist like XLM-RoBERTa suffices when its tokenizer aligns

9. MLLP-VRAIN UPV system for the IWSLT 2026 Simultaneous Speech Translation task

   http://arxiv.org/abs/2606.17255v1 · arxiv

   This work describes the participation of the MLLP-VRAIN research group in the shared task of the IWSLT 2026 Simultaneous Speech Translation track. Our submission utilizes the recently released Parakeet and Qwen 3.5 models to create a robust, cascaded solution for long-form SimulST through the use of

10. VISA: A Visual Information Strengthened Audio-Reasoning System for the Interspeech 2026 ARC Agent Track

    http://arxiv.org/abs/2606.07264v2 · arxiv

    Audio reasoning requires multi-step, evidence-grounded inference over temporally dynamic and acoustically mixed signals, exceeding conventional perception tasks such as ASR or captioning. We present VISA, our submission to the Interspeech 2026 Audio Reasoning Challenge (Agent Track), evaluated via t

10 hasil · 662 md