AI 论文与研究

effort 到底是什么？什么时候该调整它，为什么不对所有任务都用最大 effort？ 我深入研究了这个问题，查看了评测数据并做了自己的测试，结果让我相当意外。https://x.com/i/article/2103535187426709504

Qwen 团队发布报告，介绍 Qwen3.8-Omni-Flash，一个原生多模态模型，面向跨文本、音频和视频的长程智能体任务，如视频编辑和长音频视频翻译。模型采用 Qwen3.8-Next 的稀疏 MoE 架构，上下文窗口达一百万 token，并通过协同训练策略在保持文本性能的同时将智能体能力迁移到音频和视频任务。

Qwen 团队发布 Qwen3.8-Omni-Flash 报告，这是一个原生多模态模型，面向跨文本、音频和视频的长时程智能体任务，如视频编辑和长音频视频翻译。模型沿用 Qwen3.8-Next 的稀疏 MoE 架构，上下文窗口为 100 万 token，并通过协同训练策略在保持文本性能的同时把智能体能力迁移到音频和视频任务。

慕尼黑 CESifo 的 Robert Fairlie 和 Jane Wu 发布工作论文，称没有证据显示应届大学毕业生在绝对或相对水平上出现明显的岗位替代或招聘减少。

Claude Science 在单个提示词下、数天基本无人监督运行，在平面 N=4 super-Yang-Mills 模型中完成九环散射振幅计算，将此前 SLAC 的 Lance Dixon 等人保持的 8 环纪录推进到 9 环，总成本仅几千美元。

Reasoning models often generate very long reasoning traces, making inference computationally expensive. Existing approaches typically improve efficiency either through inference-time early-stopping mechanisms or by explicitly encouraging s…

We give a gap-free differentially private algorithm for the principal component analysis (PCA) problem with Gaussian data.

Recent literature has shown a strong connection between optimization and sampling. We develop the corresponding first-order theory for diffusion models. First, the SDE-based reverse-time flows of overdamped and underdamped Langevin diffusi…

Generative AI systems are increasingly used, but aligning their outputs with user requirements poses a continuing challenge. Here, we aim to ensure that the distribution of an attribute of an AI-generated output aligns with a user-specifie…

Large language models (LLMs) implicitly infer attributes of their users and adapt their behavior accordingly, yet these beliefs remain difficult to inspect and causally manipulate. We introduce Belief Self-Distillation (BSD), a unified rea…

Low-rank adapters (LoRA) make it cheap to fine-tune a large language model once per task, but combining several independently trained adapters into one model remains difficult: merging the updates in weight space causes interference, retra…

Anthropic 在科学博客称，物理学家 @4gravitons 发起挑战后，Claude 在 Claude Science 中依据单个提示词 largely unsupervised 地运行数天，在平面 N=4 超杨-米尔斯模型中完成九圈散射振幅计算，总成本约几千美元。

Direct feedback alignment (DFA) trains hidden layers through fixed random projections of output error. With tanh hidden units and independent sigmoid outputs, plain stochastic gradient descent can stall near the loss of a constant predicto…

在世界模型中训练客体永久性 论文：https://huggingface.co/papers/2609.28654

We investigate whether natural-language documentation helps coding agents resolve software issues, and we build the tools to construct and evaluate it. We introduce a roundtrip benchmark that scores code descriptions by whether code regene…

Decision Transformer performance degrades on long rollouts because the conditioning context drifts out of the training distribution. We show that this drift is visible through the model's own next state prediction error, which rises during…

Uneven rotation and dropped frames make equal-angle assumptions unreliable for turntable reconstruction. We present OC-GS, an object-centric Gaussian splatting that refines each image's angle while maintaining a shared camera, rotation axi…

Many LLM training and inference methods, including RL and test-time scaling, depend on repeated sampling, but benefit only when the responses meaningfully differ. Self-training faces the same challenge: training data is typically construct…

Deep learning has substantially accelerated the calibration of complex stochastic-volatility models, but neural point calibration alone does not capture the uncertainty remaining after an implied-volatility (IV) surface has been observed. …

Conversational AI tools are entering children's everyday experiences, and schools are interested in adopting them. However, successful classroom integration depends not only on the technology but also on the work teachers do to make it usa…

AI tutoring could markedly improve learning outcomes for students in developing regions such as Vietnam, yet the two obvious paths both fall short. Cloud assistants such as ChatGPT route sensitive student data to foreign servers---violatin…

We show that neural network weights can be explicilty fintuned to admit a smaller grammar. Weight Pair Encoding (WeightPE) does so by placing a lossy Re-Pair compressor inside a straight-through estimator. The int8 weights of the network a…

Multi-agent LLM systems are often expected to improve as team size increases, yet the scaling behavior may depend on task structure. Our central contribution is to introduce Steiner's taxonomy of group tasks as a framework for analyzing mu…

Large neural networks can be compressed by rounding or "quantizing" their weights to numbers that admit representations with fewer bits. One algorithm for quantization, OPTQ, progressively quantizes the weights of a neural network so that …

Online learning in non-stationary environments requires models to adapt rapidly from streaming data under strict computational constraints. A principled approach casts online learning as Bayesian state tracking, where model parameters are …

Ensuring online safety through content monitoring had raised Hate Speech Detection as a crucial task to be addressed. By essence the task demands the capture of contextual cues, which are essential for a precise understanding of the conten…

Disaggregating the two stages, Prefill and Decode, onto separate GPU pools is now a standard optimization for (text-only) LLM serving. However, multimodal LLMs (MLLMs), which add a third phase, Encode, pose new challenges for resource allo…

NaceAI 推出 Drex，一个 sub-6B 决策模型，不生成文本而是直接输出各选项概率，一次前向即可完成，面向智能体路由、工具选择、重排序与策略检查等场景。Drex 采用小型扩散模型加 RLAF 架构，定价 $0.04/1M input tokens，延迟低于 1 秒，在 Decision Index 上排名 #1，40 项 benchmark 中赢下 23 项，开放权重与技术报告即将发布。

非常高兴发布 SmolDataEnvs：5,000 个可验证的 RL 环境任务，用于在代码和数据科学领域爬坡训练小模型，由 @adithya_s_k 完成 100% 开源：环境、评测、训练！ https://huggingface.co/datasets/FineEnvs/SmolDataEnvs

Large language models (LLMs) have demonstrated promising performance in log anomaly detection, yet how their adaptation strategies, architectures, and deployment configurations affect detection effectiveness remains insufficiently understo…

Tree-Adjoining Grammars (TAGs) have recently been introduced to Nonlinear System Identification (NLSI) as a means of encoding an entire model class as a finite set of grammatical rules, from which candidate models are assembled as trees. E…

RSIAgent 用课程智能体生成练习任务、执行智能体用代码解题、独立验证器校验结果，练习先覆盖相关任务再深入真实任务的难例。论文称，先广泛探索再攻难例的智能体在 4 项任务上平均得分 74.54%，直接上手难例仅 56.50%。该方法旨在替代为新应用收集数据并重训的高成本做法。

Distributionally robust optimization (DRO) provides a principled framework for learning under distribution shift, but its practical use is hindered by the difficulty of evaluating worst-case risks for nonconvex loss functions. We study a p…

Inference in LLMs is conventionally a fixed-depth, fixed-order forward pass through every layer, regardless of how difficult the input is. The human brain does not work this way: using the thalamus as a central hub, it routes information f…

The Model Context Protocol (MCP) provides a common interface through which AI applications discover and use external resources and tools. It allows language-model agents to ground their reasoning in current system state and interact with h…

Vision-Language Models (VLMs) exhibit remarkable zero-shot generalization, yet they often encode unwanted or hazardous stylistic domains such as idealized textbook diagrams in medical AI or cartoon vehicles in autonomous driving. Approxima…

Contemporary large language model (LLM) chat systems treat conversation history as an immutable sequence of turns that defines the model's working context. However, user intent in real interactions is not static: it evolves through correct…

Time-series carry structure simultaneously at multiple scales (fine-grained variation, mid-range motifs, and global properties) and downstream tasks operate at correspondingly different scales. Most existing self-supervised learning approa…

Humyn Labs 推出 BRIDGE ASR 2.0，用真实双人对话评测 23 个语音识别模型，覆盖 18 种印度语言及西班牙语、葡萄牙语、越南语。其核心指标 code-switch F1 检验句中混用的英文词是否保持英文，排行榜支持按语言和指标筛选，方法论与评测数据公开。

Large video diffusion models offer expressive priors for embodied prediction and learning, yet their many-step sampling remains costly for interactive downstream use. Distribution Matching Distillation (DMD) enables few-step video generati…