MLINFO COLLECTION
LoRA、RLHF、SFT、軽量ファインチューニングなど、LLMを用途に合わせる技術を扱います。
Existing vision-language models (VLMs) remain unreliable for fine-grained visual perception. In this report, we present WeVisOne-VL (WeChat Vision All-in-One), a powerful VLM that unifies…
Mathematical supervision for language models is typically flattened into isolated problem-solution pairs, discarding the curricular organization and evidential structure of the original sources. We…
Decoding sensory-evoked functional magnetic resonance imaging (fMRI) data is a central analytical tool in cognitive neuroscience. Here we ask whether self-supervised learning (SSL), which has been…
In this paper, we study the regret minimization problem in episodic tabular MDPs. Our algorithm achieves the first expected regret bound scaling as $\sqrt{H^3 S A K}$ for sufficiently large $K$,…
Despite recent progress in dexterous reference tracking, existing models focus primarily on single-hand manipulation and a limited range of interactions, leaving the bimanual dexterous behaviors…
Producing long-form videos from narration requires interdependent decisions that remain coherent across shots. Existing agentic editors often use multi-stage workflows driven by general models,…
We present IQuest-Q1, a sparse Mixture-of-Experts (MoE) agentic foundation model with 320B total parameters (15B activated). IQuest-Q1 is developed through a three-stage process: (1) stable and…
Foundation models are typically trained in stages: pretraining, midtraining, supervised fine-tuning (SFT), and reinforcement learning (RL), with changes in both data and learning algorithms. We show…
While frontier vision-language models demonstrate strong capabilities in user interface (UI) navigation, their high inference costs prohibit everyday use. Conversely, smaller models trained via…
Automatic speech recognition (ASR) increasingly supplies transcripts for educational NLP, but aggregate word error rate (WER) can conceal errors concentrated in learner speech, multilingual turns,…
Scientific discovery often begins with an unexpected observation that prompts a new research question. In a world with altered physical laws, can large language models (LLMs) notice unexpected…
Parameter-efficient fine-tuning (PEFT) methods adapt large models by introducing a small number of trainable parameters. However, we find that these parameters still contain redundancy and can be…
Black-box optimization (BBO) arises in many scientific and engineering problems where objective evaluations are expensive and limited. Recent large language model (LLM) agents offer a new way to…
Spiking neural networks (SNNs) offer low-energy sequence modeling through sparse, event-driven computation. However, interactions among spike encoding, neuronal dynamics, and information propagation…
Recent advances in multimodal large language models have increased interest in interaction paradigms for video understanding. The evolution from offline to streaming and proactive interaction has…
When an LLM group's discussion is compressed into a short memory for a final decision maker, what should the memory keep? Two natural heuristics keep the rarest claims or the claims relevant to the…
Retrieval Augmented Generation (RAG) grounds large language models in external knowledge. Modern pipelines combine embedding, chunking, retrieval, reranking, query augmentation, context compression,…
In robotics, shape control (or shape servoing) refers to the automatic manipulation of a deformable object to achieve a desired shape. It involves a feedback loop that exploits the relation between…
Musculoskeletal robots combine compliant actuators with articulated skeletons, but exploring alternative configurations often requires repeated fabrication. We present MUSBRIC, a modular hardware…
Medical image segmentation is crucial for clinical diagnosis and treatment planning, requiring both global contextual understanding and fine-grained structural precision. While the Segment Anything…
Best Arm Identification (BAI) conventionally measures the cost of experimentation by the number of samples collected. In many operational settings, however, the cost of exploration relative to a…
We study contextual dynamic pricing in a non-stationary environment. In each round, a seller observes a buyer's context, posts a price, and receives only binary purchase feedback.
When a language model says "I," does it refer to its parameter weights, its currently running process, its stable preferences, its model lineage, or the goals it pursues? Different choices can assign…
This paper considers coordinating a heterogeneous team of unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs) traversing a domain containing an unknown number of potentially hazardous…