In this paper, we present our submission to SemEval-2025 Task 8: Question Answering over Tabular Data. This task, evaluated on the DataBench dataset, assesses Large Language Models' (LLMs) ability to answer natural language questions over structured data while addressing topic diversity and table size limitations in previous benchmarks. We propose a system that employs effective LLM prompting to translate natural language queries into executable code, enabling accurate responses, error correction, and interpretability. Our approach ranks first in both subtasks of the competition in the proprietary model category, significantly outperforming the organizer's baseline.

Large Language Models (LLMs) have demonstrated substantial potential in addressing complex reasoning tasks, yet their general-purpose nature often limits their effectiveness in specialized domains such as maritime navigation. To bridge this gap, we introduce Llamarine, the first open-source LLM designed specifically for maritime navigation. Llamarine 1.0 is developed through continued pretraining and fine-tuning on a high-quality corpus comprising maritime textbooks, research publications, and web text from Wikipedia. This domain-specific training enables the model to acquire expert-level knowledge in navigational principles, collision avoidance, route optimization, and regulatory compliance. Our key contributions include (a) the curation of a comprehensive maritime dataset from authoritative sources, ensuring depth and reliability in the model's knowledge base; (b) the development of a foundational model capable of reasoning about complex navigational challenges with greater accuracy than general-purpose LLMs; and (c) the establishment of a benchmark to evaluate performance in maritime-specific decision-making tasks. Experimental results demonstrate that Llamarine outperforms both general-purpose and commercial LLMs in critical navigation-related tasks, such as trajectory planning, risk assessment, and compliance with maritime regulations. By providing an open-source foundation model trained exclusively on high-quality maritime literature, Llamarine paves the way for AI-driven advancements in maritime safety, efficiency, and operational decision-making.

Large Language Models (LLMs) and LLM-based agents show great promise in accelerating scientific research. Existing benchmarks for measuring this potential and guiding future development continue to evolve from pure recall and rote knowledge tasks, towards more practical work such as literature review and experimental planning. Bioinformatics is a domain where fully autonomous AI-driven discovery may be near, but no extensive benchmarks for measuring progress have been introduced to date. We therefore present the Bioinformatics Benchmark (BixBench), a dataset comprising over 50 real-world scenarios of practical biological data analysis with nearly 300 associated open-answer questions designed to measure the ability of LLM-based agents to explore biological datasets, perform long, multi-step analytical trajectories, and interpret the nuanced results of those analyses. We evaluate the performance of two frontier LLMs (GPT-4o and Claude 3.5 Sonnet) using a custom agent framework we open source. We find that even the latest frontier models only achieve 17% accuracy in the open-answer regime, and no better than random in a multiple-choice setting. By exposing the current limitations of frontier models, we hope BixBench can spur the development of agents capable of conducting rigorous bioinformatic analysis and accelerate scientific discovery.

Large Language Models (LLMs) have achieved remarkable success in various natural language processing tasks, yet their ability to generate long-form content remains poorly understood and evaluated. Our analysis reveals that current LLMs struggle with length requirements and information density in long-text generation, with performance deteriorating as text length increases. To quantitively locate such a performance degradation and provide further insights on model development, we present LongEval, a benchmark that evaluates long-text generation through both direct and plan-based generation paradigms, inspired by cognitive and linguistic writing models. The comprehensive experiments in this work reveal interesting findings such as that while model size correlates with generation ability, the small-scale model (e.g., LongWriter), well-trained on long texts, has comparable performance. All code and datasets are released in https://github.com/Wusiwei0410/LongEval.

The Mixture-of-Experts (MoE) structure scales the Transformer-based large language models (LLMs) and improves their performance with only the sub-linear increase in computation resources. Recently, a fine-grained DeepSeekMoE structure is proposed, which can further improve the computing efficiency of MoE without performance degradation. However, the All-to-All communication introduced by MoE has become a bottleneck, especially for the fine-grained structure, which typically involves and activates more experts, hence contributing to heavier communication overhead. In this paper, we propose a novel MoE structure named BigMac, which is also fine-grained but with high communication efficiency. The innovation of BigMac is mainly due to that we abandon the \textbf{c}ommunicate-\textbf{d}escend-\textbf{a}scend-\textbf{c}ommunicate (CDAC) manner used by fine-grained MoE, which leads to the All-to-All communication always taking place at the highest dimension. Instead, BigMac designs an efficient \textbf{d}escend-\textbf{c}ommunicate-\textbf{c}ommunicate-\textbf{a}scend (DCCA) manner. Specifically, we add a descending and ascending projection at the entrance and exit of the expert, respectively, which enables the communication to perform at a very low dimension. Furthermore, to adapt to DCCA, we re-design the structure of small experts, ensuring that the expert in BigMac has enough complexity to address tokens. Experimental results show that BigMac achieves comparable or even better model quality than fine-grained MoEs with the same number of experts and a similar number of total parameters. Equally importantly, BigMac reduces the end-to-end latency by up to 3.09$\times$ for training and increases the throughput by up to 3.11$\times$ for inference on state-of-the-art AI computing frameworks including Megatron, Tutel, and DeepSpeed-Inference.

Long context understanding remains challenging for large language models due to their limited context windows. This paper presents Long Input Fine-Tuning (LIFT), a novel framework for long-context modeling that can improve the long-context performance of arbitrary (short-context) LLMs by dynamically adapting model parameters based on the long input. Importantly, LIFT, rather than endlessly extending the context window size to accommodate increasingly longer inputs in context, chooses to store and absorb the long input in parameter. By fine-tuning the long input into model parameters, LIFT allows short-context LLMs to answer questions even when the required information is not provided in the context during inference. Furthermore, to enhance LIFT performance while maintaining the original in-context learning (ICL) capabilities, we introduce Gated Memory, a specialized attention adapter that automatically balances long input memorization and ICL. We provide a comprehensive analysis of the strengths and limitations of LIFT on long context understanding, offering valuable directions for future research.

Large language models (LLMs) such as GPTs and Mixtral-8x7B have revolutionized machine intelligence due to their exceptional abilities in generic ML tasks. Transiting LLMs from datacenters to edge devices brings benefits like better privacy and availability, but is challenged by their massive parameter size and thus unbearable runtime costs. To this end, we present EdgeMoE, an on-device inference engine for mixture-of-expert (MoE) LLMs -- a popular form of sparse LLM that scales its parameter size with almost constant computing complexity. EdgeMoE achieves both memory- and compute-efficiency by partitioning the model into the storage hierarchy: non-expert weights are held in device memory; while expert weights are held on external storage and fetched to memory only when activated. This design is motivated by a key observation that expert weights are bulky but infrequently used due to sparse activation. To further reduce the expert I/O swapping overhead, EdgeMoE incorporates two novel techniques: (1) expert-wise bitwidth adaptation that reduces the expert sizes with tolerable accuracy loss; (2) expert preloading that predicts the activated experts ahead of time and preloads it with the compute-I/O pipeline. On popular MoE LLMs and edge devices, EdgeMoE showcase significant memory savings and speedup over competitive baselines. The code is available at https://github.com/UbiquitousLearning/mllm.

As specialized large language models (LLMs) become increasingly prevalent, model merging methods are being used to combine them to create a single multi-task model without requiring any additional data or training. However, these approaches fall short when the objective of merging is to increase the downstream model's performance on a particular task-specific benchmark. In this work, we propose LEWIS (Layer Wise Sparsity), a guided model-merging framework that uses activation-based layer importance to dynamically adjust layer-wise task-vector sparsity required for the merge process. LEWIS uses a calibration dataset to prioritize critical layers during the task-vector pruning process required for model merging. This approach guides existing merging methods by preserving essential layer-wise task-specific knowledge while ensuring the merged model performs the best at benchmarks resembling the calibration dataset. Our experiments demonstrate the effectiveness of LEWIS with performance improvements of code instruction-following and math-solving models created through model merging up to 4 percent and 11.3 percent, respectively, outperforming unguided data-less model merging approaches that use uniform-sparsity.

Despite all the industry hype and genuine advances, generative AI models are still prone to odd, inexplicable, and downright worrisome quirks. According to recent evidence, the industry's newer reasoning models may already possess the ability to manipulate and circumvent their human programmers' goals. Some AI will even attempt to cheat their way out of losing in games of chess. This poor sportsmanship is documented in a preprint study from Palisade Research, an organization focused on risk assessments of emerging AI systems. While supercomputers--most famously IBM's Deep Blue--have long surpassed the world's best human chess players, generative AI still lags behind due to their underlying programming parameters.

"It reflects the broader competitiveness of China's frontier AI ecosystem," says Scott Singer, a visiting scholar in the Technology and International Affairs Program at the Carnegie Endowment for International Peace. That ecosystem includes DeepSeek's R1 and Tencent's Hunyuan model, which Anthropic co-founder Jack Clark has said is by some measures "world-class." That said, assessments of Alibaba's latest model are preliminary, both due to the inherent challenge of measuring model capabilities, and because so far, the model has only been assessed by Alibaba itself. "The information environment is not very rich right now," says Singer. Since the release of DeepSeek's R1 model in January sent waves through the global stock market, China's tech ecosystem has been in the spotlight--particularly as the U.S. increasingly sees itself as racing against China to create artificial general intelligence (AGI)--highly advanced AI systems capable of performing most cognitive work, from graphic design to machine-learning research.