Despite rapid progress, ASR evaluation remains saturated with short-form English, and efficiency is rarely reported. We present the Open ASR Leaderboard, a fully reproducible benchmark and interactive leaderboard comparing 60+ open-source and proprietary systems across 11 datasets, including a dedicated multilingual track. We standardize text normalization and report both word error rate (WER) and inverse real-time factor (RTFx), enabling fair accuracy-efficiency comparisons. For English transcription, Conformer encoders paired with LLM decoders achieve the best average WER but are slower, while CTC and TDT decoders deliver much better RTFx, making them attractive for long-form and offline use. Whisper-derived encoders fine-tuned for English improve accuracy but often trade off multilingual coverage. All code and dataset loaders are open-sourced to support transparent, extensible evaluation.

The 2025 Multimodal Models for Low-Resource Contexts and Social Impact (MMLoSo) Language Challenge addresses one of India's most pressing linguistic gaps: the lack of resources for its diverse low-resource languages (LRLs). In this study, we investigate whether enforcing cross-lingual similarity in specific internal layers of a decoder-only multilingual large language model (LLM) can improve translation quality from LRL to high-resource language (HRL). Specifically, we combine Centered Kernel Alignment (CKA), a similarity metric that encourages representations of different languages to align, with REPINA, a regularization method that constrains parameter updates to remain close to the pretrained model, into a joint method we call TRepLiNa. In this research project, we experiment with zero-shot, few-shot, and fine-tuning settings using Aya-23 8B with QLoRA across MMLoSo shared task language pairs (Mundari, Santali, Bhili) with Hindi/English pivots. Our results show that aligning mid-level layers using TRepLiNa (CKA+REPINA) is a low-cost, practical approach to improving LRL translation, especially in data-scarce settings.

We present OneFlow, the first non-autoregressive multimodal model that enables variable-length and concurrent mixed-modal generation. Unlike autoregressive models that enforce rigid causal ordering between text and image generation, OneFlow combines an insertion-based Edit Flow for discrete text tokens with Flow Matching for image latents. OneFlow enables concurrent text-image synthesis with hierarchical sampling that prioritizes content over grammar. Through controlled experiments across model sizes from 1B to 8B, we demonstrate that OneFlow outperforms autoregressive baselines on both generation and understanding tasks while using up to 50% fewer training FLOPs. OneFlow surpasses both autoregressive and diffusion-based approaches while unlocking new capabilities for concurrent generation, iterative refinement, and natural reasoning-like generation.

False information poses a significant global challenge, and manually verifying claims is a time-consuming and resource-intensive process. In this research paper, we experiment with different approaches to investigate the effectiveness of large language models (LLMs) in classifying factual claims by their veracity and generating justifications in English and Telugu. The key contributions of this work include the creation of a bilingual English-Telugu dataset and the benchmarking of different veracity classification approaches based on LLMs.

State-of-the-art (SOTA) Text-to-SQL methods still lag significantly behind human experts on challenging benchmarks like BIRD. Current approaches that explore test-time scaling lack an orchestrated strategy and neglect the model's internal reasoning process. To bridge this gap, we introduce Agentar-Scale-SQL, a novel framework leveraging scalable computation to improve performance. Agentar-Scale-SQL implements an Orchestrated Test-Time Scaling strategy that synergistically combines three distinct perspectives: i) Internal Scaling via RL-enhanced Intrinsic Reasoning, ii) Sequential Scaling through Iterative Refinement, and iii) Parallel Scaling using Diverse Synthesis and Tournament Selection. Agentar-Scale-SQL is a general-purpose framework designed for easy adaptation to new databases and more powerful language models. Extensive experiments show that Agentar-Scale-SQL achieves SOTA performance on the BIRD benchmark, reaching 81.67% execution accuracy on the test set and ranking first on the official leaderboard, demonstrating an effective path toward human-level performance.

In this technical note, we study the problem of inverse permutation learning in decoder-only transformers. Given a permutation and a string to which that permutation has been applied, the model is tasked with producing the original (``canonical'') string. We argue that this task models a natural robustness property across a variety of reasoning tasks, including long-context retrieval, multiple choice QA and in-context learning. Our primary contribution is an impossibility result: we show that an arbitrary depth, decoder-only transformer cannot learn this task. This result concerns the expressive capacity of decoder-only transformer models and is agnostic to training dynamics or sample complexity. We give a pair of alternative constructions under which inverse permutation learning is feasible. The first of these highlights the fundamental role of the causal attention mask, and reveals a gap between the expressivity of encoder-decoder transformers and the more popular decoder-only architecture. The latter result is more surprising: we show that simply padding the input with ``scratch tokens" yields a construction under which inverse permutation learning is possible. We conjecture that this may suggest an alternative mechanism by which chain-of-thought prompting or, more generally, intermediate ``thinking'' tokens can enable reasoning in large language models, even when these tokens encode no meaningful semantic information (e.g., the results of intermediate computations).

AI-based climate and weather models have rapidly gained popularity, providing faster forecasts with skill that can match or even surpass that of traditional dynamical models. Despite this success, these models face a key challenge: predicting future climates while being trained only with historical data. In this study, we investigate this issue by analyzing boreal winter land temperature biases in AI weather and climate models. We examine two weather models, FourCastNet V2 Small (FourCastNet) and Pangu Weather (Pangu), evaluating their predictions for 2020-2025 and Ai2 Climate Emulator version 2 (ACE2) for 1996-2010. These time periods lie outside of the respective models' training sets and are significantly more recent than the bulk of their training data, allowing us to assess how well the models generalize to new, i.e. more modern, conditions. We find that all three models produce cold-biased mean temperatures, resembling climates from 15-20 years earlier than the period they are predicting. In some regions, like the Eastern U.S., the predictions resemble climates from as much as 20-30 years earlier. Further analysis shows that FourCastNet's and Pangu's cold bias is strongest in the hottest predicted temperatures, indicating limited training exposure to modern extreme heat events. In contrast, ACE2's bias is more evenly distributed but largest in regions, seasons, and parts of the temperature distribution where climate change has been most pronounced. These findings underscore the challenge of training AI models exclusively on historical data and highlight the need to account for such biases when applying them to future climate prediction.

This paper synthesizes a series of formal proofs to construct a unified theory on the logical limits of the Symbol Grounding Problem. We distinguish between internal meaning (sense), which formal systems can possess via axioms, and external grounding (reference), which is a necessary condition for connecting symbols to the world. We demonstrate through a four-stage argument that meaningful grounding within a formal system must arise from a process that is external, dynamic, and non-fixed algorithmic. First, we show that for a purely symbolic system, the impossibility of grounding is a direct consequence of its definition. Second, we extend this limitation to systems with any finite, static set of pre-established meanings (Semantic Axioms). By formally modeling the computationalist hypothesis-which equates grounding with internal derivation-we prove via Gödelian arguments that such systems cannot consistently and completely define a "groundability predicate" for all truths. Third, we demonstrate that the "grounding act" for emergent meanings cannot be inferred from internal rules but requires an axiomatic, meta-level update. Drawing on Turing's concept of Oracle Machines and Piccinini's analysis of the mathematical objection, we identify this update as physical transduction. Finally, we prove that this process cannot be simulated by a fixed judgment algorithm, validating the logical necessity of embodied interaction.

Loss of trainability refers to a phenomenon in continual learning where parameter updates no longer make progress on the optimization objective, so accuracy stalls or degrades as the learning problem changes over time. In this paper, we analyze loss of trainability through an optimization lens and find that the phenomenon is not reliably predicted by existing individual indicators such as Hessian rank, sharpness level, weight or gradient norms, gradient-to-parameter ratios, and unit-sign entropy. Motivated by our analysis, we introduce two complementary indicators: a batch-size-aware gradient-noise bound and a curvature volatility-controlled bound. We then combine these two indicators into a per-layer adaptive noise threshold on the effective step-size that anticipates trainability behavior. Using this insight, we propose a step-size scheduler that keeps each layer's effective parameter update below this bound, thereby avoiding loss of trainability. We demonstrate that our scheduler can improve the accuracy maintained by previously proposed approaches, such as concatenated ReLU (CReLU), Wasserstein regularizer, and L2 weight decay. Surprisingly, our scheduler produces adaptive step-size trajectories that, without tuning, mirror the manually engineered step-size decay schedules.

Each year millions of people seek help for their legal problems by calling a legal aid program hotline, walking into a legal aid office, or using a lawyer referral service. The first step to match them to the right help is to identify the legal problem the applicant is experiencing. Misdirection has consequences. Applicants may miss a deadline, experience physical abuse, lose housing or lose custody of children while waiting to connect to the right legal help. We introduce and evaluate the FETCH classifier for legal issue classification and describe two methods for improving accuracy: a hybrid LLM/ML ensemble classification method, and the automatic generation of follow-up questions to enrich the initial problem narrative. We employ a novel data set of 419 real-world queries to a nonprofit lawyer referral service. Ultimately, we show classification accuracy (hits@2) of 97.37\% using a mix of inexpensive models, exceeding the performance of the current state-of-the-art GPT-5 model. Our approach shows promise in significantly reducing the cost of guiding users of the legal system to the right resource for their problem while achieving high accuracy.