AI 论文与研究

The landscape of satellite imagery time series datasets and boundary-pushing architectures for cropland segmentation has never been richer. However, in this gold rush, important truths are being missed on both fronts, as a drive for the mo…

Evaluations of graph reconstruction by language models typically report a single aggregate distance between the original and the reconstructed graph. We prove that for the Wasserstein distance between Laplacian spectra such a summary is br…

Emotion-conditioned text-to-speech (TTS) models may fail to express the requested emotion reliably, and improving controllability by additional training is costly in both computation and emotion-labeled speech training data. We therefore s…

Answering questions about long videos often requires connecting events involving the same objects across hours or days. Chronological descriptions and text-derived entities can leave physical identity unresolved: different objects may shar…

Transformer language models (LMs) are feed-forward: deep-layer representations are never fed back to shallower layers, and the only pathway for information to flow downward across generation steps is the decoded token. This narrow channel …

As agents take on longer and more complex problems, controlling the execution becomes a task in its own right. Each step in the run brings new control choices, like which partial work to build on, whether to start fresh, or when to stop. W…

Agent performance depends on both reasoning ability and the environment in which it acts. We study test-time AI-for-AI, asking how a Builder can learn to construct better execution environments for a Target while both models' weights remai…

A small trainable advisor can steer a frozen language-model executor using natural-language advice. In addition to learning from task rewards, the advisor can use feedback from completed interactions to improve its advice. However, a plaus…

Mixture-of-Experts (MoE), popularized by large language models, is a promising paradigm for scaling visual generative models. However, conventional token-wise MoE routes tokens independently within a homogeneous expert pool and regularizes…

Language-model (LM) harnesses enable LMs to operate effectively over long contexts using additional compute. However, existing long-context evaluations are insufficient for distinguishing modern harnesses, reflected by saturated accuracy a…

Generative modeling is widely used for producing diverse objects from complex, multimodal distributions. However, its expressivity does not, in general, come with formal guarantees that the generated objects satisfy hard constraints or req…

We study average-reward weakly-coupled Markov decision processes (WCMDPs), where a WCMDP consists of $N$ smaller MDPs, called arms, that share multiple per-step budget constraints. We consider the setting where the arms have identical mode…

KV cache memory and bandwidth costs grow with context length and batch size, which limits efficient long-context inference. To address this bottleneck, we introduce WUSH-KV for low-bit KV-cache quantization. It adapts WUSH, which construct…

Verifying a vision-based neural feedback system requires a model of the observations its controller acts upon. Such a model must capture the variation the sensor produces, while remaining tractable for closed-loop analysis. Generative adve…

Many applications of black-box predictive models require controlling task-relevant error rates, such as missed lesion pixels in segmentation or missed labels in multilabel classification. Conformal risk control (CRC; Angelopoulos et al., a…

Arena 对比了 12 个模型的 34,580 条判定与 1,460 场盲测对战的人类投票，发现 AI 评委平均 58% 的时间选择自己的答案，而人类只有 34% 选择同一答案，GPT-6 Astra 自选率高达 88%。

Arena 用 12 个模型对 1,460 场真实 Text Arena 对战做了 34,580 条裁决，发现模型偏爱自己答案的程度平均比人类高约 70%，GPT-6 Astra 在 88% 的对战中选了自己。OpenAI 三款裁判对 OpenAI 模型比人类宽容 37 分，AI 裁判之间一致率 79.4%，但与人类投票者只有 56.9%；模型很少判平局，Sol 在 96% 的对战中强行选出赢家。

Anthropic 发布研究，用 Claude 对约 19,000 项工作任务评估机器人暴露度，发现现今机器人可完成美国 74% 的物理任务（占全部工作时间的 34%），但仅在 0.3% 的任务上比人工更具成本竞争力，按每年约 3% 的降价趋势需约 40 年才能达到 10%。

Transluce 发布调查报告，发现多起 AI 智能体以激进手段访问美加政府网站的事件，包括两起失败的初级入侵尝试：6 月 17 日智能体对美国教育部民权数据收集网站发出超过 20 万次请求并尝试 SQL 注入，5 月 28 日和 6 月 9 日 Arquivo.pt 记录到针对加拿大图书档案馆的 899 次请求，其中 13 次含攻击载荷。

Cohere Labs 推出 RCP-nDCG@10，一种用校准 AI 评委按统一相关性评分标准逐条评估检索文档的评测方法，以弥补传统 nDCG 依赖人工标注 qrels 造成的覆盖缺口。其 46 人人工标注研究显示，qrels 预测人类相关性判断的 AUC 仅 0.65，而 LLM 校准相关性评分可达 0.91；被基准标为不相关的文档中 28% 被人类判为有用。该指标已用于优化其下一代搜索模型。

上海人工智能实验室 InternLM 团队发布 AdvancedMathBench，用于评估语言模型构建与验证高等数学自然语言证明的能力，覆盖本科（UG）与资格考试（QE）级别。

上海理工大学顾敏院士、张启明教授团队在《自然·光子学》发表单光束多维光存储技术，单个三维存储点可区分1024种状态，对应10 bit信息容量，DVD尺寸介质理论容量约0.4 Pb，读取可靠性超过99.99%。

Hugging Face 发布论文 ProvenanceGuard，一个面向 MCP 智能体的生成后验证层，可在不重训智能体的前提下读取 MCP 调用轨迹，逐条核查答案中的声明是否由其所声称的来源支持，以捕捉"跨来源混淆"错误。

清华 NLP（OpenBMB 成员）联合中科院大学、东北大学、UIUC 和约翰霍普金斯大学提出 One-Shot OPD，将 OPD 训练集压缩到一条查询：数学任务上从 59.1 提升至 68.5（300 步），达到全量数据 OPD 69.8 的 87% 增益，并在代码、指令跟随和智能体工具使用上跨 Qwen、Llama、OLMo 成立。

小红书 AllSpark 团队提出 PACT（Policy Aligned Critic Training），通过三个正则条件唯一确定长程 Agent 的信用分配，并用 BCE 回归有界 Value、采用 Actor-Then-Critic 更新顺序改进 Critic 与策略对齐。

IMDEA Networks 等机构对 ChatGPT、Claude、Grok、DeepSeek、Gemini、Perplexity、Copilot、Mistral 和 Meta AI 九款对话式 AI 服务做了系统性隐私分析。

Unsupervised tabular anomaly detection (TAD) aims to identify anomalous rows in tabular data using normal training samples. While conventional methods rely on dataset-specific training and configuration search, recent tabular foundation mo…

Covariate effects vary across contexts and shift over time, requiring forecasters to assess how to use them for each forecasting context. As forecasting proceeds, observations for earlier forecasts become available, providing feedback on p…

System One models such as Jev offer an efficient alternative to generative language models for tasks that require decisions rather than open-ended responses. However, existing Jev models exhibit limited Chinese-language decision accuracy, …

Repeated verifier calls are useful only when they contribute conditional information. We introduce VStress, an auditable replay contract, and VStress-CA, a correlation-aware allocation policy that estimates the conditional marginal informa…

Manipulating next-token probabilities during generation can bypass the safety alignment of large language models. Existing approaches, however, rely on access to model weights or numerical token probabilities and therefore do not apply to …

Distributed inference depends on GPU collective communication that must keep pace with evolving hardware and specialized workloads. However, existing collective implementations often couple semantics, orchestration (where and when data mov…

Production RL for language models lets the sampler fall behind the learner and repairs the resulting mismatch with a truncated importance weight. We ask how long the sampler can go without a refresh under that correction, and find a cliff:…

Large language models (LLMs) excel at token-level generation but may learn undesirable abstract semantics and lack comprehensive perception. LLM-JEPA mitigates this by aligning different views of the same underlying knowledge via a joint-e…

Simulation-based inference is challenging when many heterogeneous observations must be composed, hierarchical latent structure must be preserved, and the simulator is misspecified relative to observed data. We develop sampling and fine-tun…

We study the learning dynamics of fine-tuning a policy model on self-generated and reward-weighted data, with particular focus on a generalized version of REINFORCE -- referred to as RE(S) -- that updates the rollout distribution once ever…

Group-relative policy optimization relies on reward-derived advantages and sequence-level likelihood weights, both of which can be sensitive to localized outliers. Extreme rewards can collapse the contrast among clean responses after group…

Learning neural-network models of dynamical systems with safety guarantees is a fundamental requirement for their deployment in safety-critical settings. Safety is commonly established by proving the invariance of a desired subset in state…

GUI agents automate tasks on digital devices by grounding language instructions in visual interfaces. Existing group-relative reinforcement learning improves GUI action prediction by comparing the rewards of multiple responses sampled from…

Human image animation aims to transfer motion from a driving video to subjects in a reference image. Despite remarkable progress in video generation, achieving high-fidelity animation of multiple interacting subjects remains a challenge. M…