AI 论文与研究

Anthropic 宣布 Claude 在噬菌体 DNA 中发现一个此前未知的酶系统，其基因旁有一段类似 CRISPR 的重复 DNA 阵列。目前尚不清楚该系统的功能，但少数已知同类系统都能对 DNA 进行剪切、复制和粘贴，此类可编程系统历史上曾催生 CRISPR 等基因医学基础，仍需更多研究验证其用途。

Representation Autoencoders (RAEs) enable diffusion models to operate in the feature spaces of pretrained visual encoders. However, many off-the-shelf encoders are not optimized for faithful reconstruction, discarding fine-grained visual d…

Our results show that contrastive learning outperforms a classification-based approach to authorship verification under the tested settings. We identify loss function, batch size, training duration, pre-trained model, input context length,…

Artificial intelligence offers an unprecedented opportunity to augment human capabilities, yet progress at the frontier has focused primarily on advancing model capabilities. We introduce StudentBench, a suite of AI teaching evaluations an…

Social navigation typically assumes a specified goal and focuses on reaching it while respecting social conventions, whereas robot group joining requires predicting where to join based on the group's real-time activity and formation. This …

We introduce Sharper Transductive Local Complexity (STLC), a localized complexity method for transductive learning under uniform sampling without replacement. The construction starts from a Bernstein-type concentration inequality for the s…

Large language models (LLMs) are increasingly used in coding tasks, but their ability to reason about code execution remains unclear. Existing repository-level QA benchmarks mainly evaluate static code understanding and often rely on LLM-b…

We study the nonequilibrium dynamics of a minimal recurrent transformer with $N$ normalized tokens, $Q=K=I$, and a negative value map $V=-I$. Similarity-based attention selects nearby representations, while the negative value map drives to…

Reordering a set of mathematical rules without changing its meaning should preserve the correct answer, but must a model's internal representations stay invariant too? We investigate this question using synthetic multi-step function-compos…

这既有趣，也有用地衡量了多模态 AI 在短时间内进步了多少。 [引用 @EpochAIResearch]：AI 能看出你的 IKEA 家具装错了吗？我们的新基准 Furniture Assembly Benchmark（FAB）给模型提供说明书和一张半成品家具的照片，让它们找出错误。 最高分在短短 10 个月内从 28% 涨到了 80%。

We study minimal-norm interpolation and $\ell_2$-regularized logistic-loss minimization for binary classification by univariate two-layer ReLU networks. We give complete geometric characterizations of the optimal classifiers in function sp…

This work addresses continuous depression-severity score prediction from clinical interview transcripts under data scarcity. We propose a sequential low-rank adaptation (LoRA) protocol for cross-scale transfer: a Qwen3 backbone with a boun…

Personalizing exoskeleton assistance across operating conditions is constrained by the time and physical effort required to collect user feedback. We examined whether a user's preference landscape varies smoothly across operating condition…

Recursive state estimation often executes approximate numerical solutions inside a feedback loop, where highly accurate local steps do not guarantee better overall results. For a fixed linear Kalman model, we characterize when a correction…

AI 能看出你把宜家家具装错了吗？我们的新基准——家具组装基准（FAB）——把说明书和一张组装到一半的家具照片交给模型，让它们找出错误。 最高分在短短 10 个月内从 28% 升到了 80%。

Recent advances in large language models (LLMs) have enabled agents to tackle long-horizon tasks across diverse environments. To further improve agent performance, existing language world models typically predict environment observations, …

Latent world models that integrate a flow in a frozen self supervised latent space train stably and cheaply, yet silently lose the property manipulation depends on most: motion. The pretrained flow never moves the manipulated object; retra…

Vector Symbolic Algebras project data structures into a hyperdimensional vector space through the application of their vector algebras to randomly generated atomic vector symbols and fractional power encodings of real-valued data. Embeddin…

Collective responses depend on individual differences, contact opportunities, and accumulated experience. Learning their dynamics from aggregate counts requires connecting a population's response distribution to both current observations a…

VoiceArena 推出 Diarization Bench，用 139 段真实对话和统一评分规则对比 12 个说话人分离系统，NVIDIA Nemotron 3 以 14.72% DER 领先。该基准还揭示 collar 效应：同一输出在 250 ms collar 下 DER 为 4.29%，换成 0 ms 则升至 14.72%，并暴露重叠语音和说话人增多时准确率的快速下降。

Language models typically construct attention values from contextual hidden states, even when some of their content may be reusable across contexts. We investigate whether token-indexed memory can replace the dedicated value projection whe…

Fine-tuning large language models on parallel data improves translation quality but can cause catastrophic forgetting. Mitigation methods are generally evaluated by retention on general benchmarks. We ask whether these findings transfer to…

Score matching has driven major advances in classical generative learning by enabling models to learn from data without evaluating intractable normalization constants, or partition functions. Yet, extending this principle to quantum learni…

Reinforcement learning with verifiable rewards (RLVR) supervises mathematical reasoning through final-answer correctness, but provides little guidance on individual tokens. On-policy distillation (OPD) supplies dense feedback on student-ge…

机器人正变得越来越智能，但它们的硬件如何跟上这种发展？微软研究院的新发现表明，将 AI 推理移出机器人本体，可以提升任务成功率、提高效率，并支持更先进的物理 AI 工作负载。https://msft.it/6014agepg

微软研究院发布关于物理AI机器人推理基础设施的研究。通过系统评估移动操作任务，发现将推理从机载GPU卸载至边缘或云端，能解决机载算力限制模型规模、导致响应延迟（最高383%）及精度下降的问题。实验显示，卸载推理不仅提升了任务成功率，还通过替换高功耗机载GPU为轻量硬件（如树莓派），使机器人电池寿命延长高达160%。此外，微软推出了基于Kubernetes的Physical AI Toolchain工具集，支持自动化容器化与分布式推理部署。

Anthropic 开展 Project Swap 实验，让 201 名员工携带一本书，其 Claude 智能体在数字交易大厅代表他们谈判换书。5 分钟聊天后，Claude 构建的图书排序与本人自评排序在 61% 的书对上一致；市场效率为 0.55（最优 0.89），其中 85% 的差距来自智能体对参与者偏好的理解不足，而非谈判表现。

Microsoft Research 等机构的论文研究多智能体在任务执行中通过共享目录通信的收益。在 ARC-AGI-3 上，k 个通信智能体的成功率匹敌 4k 个独立智能体且差距随 k 扩大；在 polyomino packing 超越 best@k 和已知最优成绩，MNIST 压缩任务中四智能体团队写出 1,957 字节、99.4% 测试准确率的分类器。

Stanford 和 Together AI 的论文提出 Self-Organizing Agent Teams（SAT），让 o3-mini、Claude Sonnet 4 和 DeepSeek-V3 组成的团队学习协作策略。

Stanford 和 Together AI 等机构的论文提出 Self-Organizing Agent Teams（SAT），让 o3-mini、Claude Sonnet 4 和 DeepSeek-V3 组成的团队从过往协作中学习可复用的协作策略。

Data assimilation estimates a dynamical state from partial and noisy observations. Classical ensemble filters are efficient but restrict analysis updates through finite sample covariance and affine Gaussian distribution. We introduce the F…

Machine-learned interatomic potentials (MLIPs) for solid-liquid interfaces in advanced materials applications, e.g., electrochemistry, catalysis and corrosion, require training data that samples both liquid environments, the solid and the …

Most Turkish-capable large language models (LLMs) are evaluated using general-purpose benchmarks rather than long, structurally complex domain documents. This paper evaluates five open-weight 7B-8B models for Turkish document question answ…

Decoder-only Transformer language models cache keys and values (KV) to reuse past computation during generation. Sharing KV across layers saves storage but reduces the diversity of representations available across depth. We study what loca…

Effective summarization of interrogative dialogues is a critical task in forensic and investigative settings, requiring high factual accuracy, coherence, and attribute-specific relevance. In this work, we introduce CASPER, a novel Chain-of…

Small and medium-sized language models offer cost-effective executors for tool-using agents, making them attractive for local and large-scale deployment. However, in long-horizon and stateful environments, they often make structural errors…

Financial institutions are beginning to deploy agentic workflows in credit, fraud, collections, compliance, and operational control. Governance remains largely component-centric: each model or agent is specified, tested, authorized, and mo…

Methods operating on Vision Transformer (ViT) feature spaces typically rely on Euclidean distance or cosine similarity. This assumes that every direction is equally meaningful, but there is no reason to believe the true task geometry has t…

Large language models (LLMs) have made substantial progress on medical question-answering, yet effective medical dialogue also requires learning to ask questions that uncover relevant patient information. To train such dialogue policies, a…

Accurate remaining discharge time (RDT) prediction is challenging in real-world battery applications because future load profiles are unknown and highly dynamic. To address the uncertainty of continuous RDT regression, this paper introduce…