Grounded multi-video question answering over real-world news events requires systems to surface query-relevant evidence across heterogeneous video archives while attributing every claim to its supporting source. We introduce CRAFT (Critic-Refined Adaptive Key-Frame Targeting), a query-conditioned pipeline that combines dynamic keyframe selection, per-video ASR with multilingual fallback, and a hybrid critic loop to iteratively verify and repair claims before consolidation. The pipeline integrates UNLI temporal entailment, DeBERTa-v3 cross-claim screening, and a Llama-3.2-3B adjudicator, with a final citation-merging stage that emits each fact once with all supporting source identifiers. On MAGMaR 2026, CRAFT achieves the best overall average (0.739), reference recall (0.810), and citation F1 (0.635). We further evaluate on a MAGMaR-style conversion of WikiVideo with 52 non-overlapping event queries, where CRAFT also performs strongly (0.823 Avg), showing that its claim-centric evidence aggregation generalizes beyond MAGMaR. Ablations show that atomic claims, ASR, and the critic loop drive the main gains over the vanilla query-conditioned baseline. Code and implementation details are publicly available at https://github.com/bhosalems/CRAFT.

Multi-video event understanding demands models that can locate and attribute query-relevant evidence scattered across long, heterogeneous video corpora. Existing large vision–language models (LVLMs) often underperform in this regime because they quickly exhaust their context budget and struggle to precisely localize evidentially important segments, frequently missing dense informational cues such as broadcast graphics, subtitles, and scoreboards. We introduce TRACE, an evidence grounding-guided framework that follows a ground-before-reasoning strategy for multi-video event reasoning. Our approach first builds a structured, text-searchable timeline for each video using OCR and object detection. A text-only LLM then conducts query-aware evidence localization, selecting relevant moments prior to any downstream visual reasoning. The retrieved frames and their grounding summaries are subsequently used to steer LVLM-based claim generation and cross-video citation consolidation. Experiments on MAGMaR 2026 and WikiVideo demonstrate that structured grounding markedly boosts factual completeness and attribution fidelity. On the MAGMaR validation split, TRACE raises macro-average MiRAGE F1 from 0.705 to 0.811 compared to an unguided Qwen3-VL-30B baseline, with especially strong improvements in citation recall (0.440 0.628). The method also attains state-of-the-art results on the official MAGMaR 2026 leaderboard.

We describe efforts to create corpora to support development and evaluation of handwriting recognition and translation technology. LDC has developed a stable pipeline and infrastructures for collecting and annotating handwriting linguistic resources to support the evaluation of MADCAT and OpenHaRT. We collect and annotate handwritten samples of pre-processed Arabic and Chinese data that has been already translated in English that is used in the GALE program. To date, LDC has recruited more than 600 scribes and collected, annotated and released more than 225,000 handwriting images. Most linguistic resources created for these programs will be made available to the larger research community by publishing in LDC's catalog. The phase 1 MADCAT corpus is now available.

This paper describes an approach to analyzing the lexical structure of OCRed bilingual dictionaries to construct resources suited for machine translation of low-density languages, where online resources are limited. A rule-based, an HMM-based, and a post-processed HMM-based method are used for rapid construction of MT lexicons based on systematic structural clues provided in the original dictionary. We evaluate the effectiveness of our techniques, concluding that: (1) the rule-based method performs better with dictionaries where the font is not an important distinguishing feature for determining information types; (2) the post-processed stochastic method improves the results of the stochastic method for phrasal entries; and (3) Our resulting bilingual lexicons are comprehensive enough to provide the basis for reasonable translation results when compared to human translations.