For anyone shipping translation systems, the hard part is still the trade-off between quality, latency, and robustness once the model leaves the lab. On the translation side, CRESiST proposes an end-to-end SimulST framework built on an omni-modal LLM that interleaves speech chunks and text tokens to avoid prefix-only decoding bottlenecks and external VAD, while the NTCIR-19 SciClaimEval overview reports a pilot task on verifying scientific claims against tables and figures in papers from machine learning, NLP, and medicine, with 22 registered teams and two subtasks: judging support and choosing between minimally edited evidence variants.

Overview of the NTCIR-19 SciClaimEval Task: Cross-modal Claim Verification in Scientific Papers

If you verify claims against figures or tables, contrastive evidence pairs and multimodal prompting matter more than single-pair scoring, because the best system drops 24.3 points without the paired choice.

This paper presents an overview of SciClaimEval, a pilot task at NTCIR-19 on verifying scientific claims against the tables and figures of the papers in which they appear. Our dataset pairs authentic claims from 180 papers in machine learning, natural language processing, and medicine with contrastive versions of their tables and figures, one supporting the claim and one minimally modified so that it does not. The task comprises two subtasks: deciding whether a piece of evidence supports a claim, and selecting which of two evidence versions does. Twenty-two teams registered, the highest number among NTCIR-19 tasks, and 14 submitted 177 runs. Most systems built on multimodal large language models, relying on prompting and multi-stage inference rather than task-specific fine-tuning. On the first subtask, the best systems reached 98.1% pair accuracy, but all six top-ranked systems relied on the contrastive pairs; the best system that judged each claim-evidence pair on its own scored 24.3 points lower. Open-weight models, embedded in carefully designed pipelines, matched proprietary ones. Yet verifying a single claim against its evidence, the setting that matters in practice, remains an open problem.

CRESiST: Self-Enhancing Explorative Policy Learning for Simultaneous Speech Translation

For simultaneous speech translation, an interleaved read-write LLM with full KV-cache reuse and self-trained read-write policies handles unbounded streams without VAD and improves the quality-latency trade-off.

Simultaneous Speech Translation (SimulST) requires balancing translation quality and latency. While Large Language Models (LLMs) excel in offline translation, current LLM-based SimulST systems predominantly rely on prefix-incremental generation. This paradigm suffers from redundant Key-Value cache recomputation and necessitates external Voice Activity Detection to process unbounded streams. To overcome these bottlenecks, we propose an end-to-end interleaved read-write framework built upon an omni-modal LLM. By interleaving speech chunks and text tokens, our architecture achieves full KV cache reuse, natively supporting segmentation-free, infinite-length inference. Furthermore, to learn optimal streaming policies without rigid offline alignments, we introduce a novel Actor-Critic self-enhancement pipeline. An RNN-T Actor dynamically samples read-write trajectories, while an LLM-based Critic evaluates these paths via intrinsic semantic and latency rewards, distilling the optimal policy back to the Actor. Extensive experiments on sentence-level (FLEURS, CoVoST2) and document-level (MuST-C, ACL 60/60) benchmarks demonstrate that our model establishes new state-of-the-art quality-latency Pareto frontiers, substantially outperforming existing cascaded and static-alignment baselines.

Papers announced by arXiv on Wednesday, 4 November 2026, covering submissions from 3 November to 4 November 2026.