AI 论文与研究

Test-time reinforcement learning (TTRL) adapts pretrained language models to unlabeled target-domain data using self-generated pseudo-labels, whose reliability remains poorly understood. We analyze majority-vote supervision for TTRL with o…

Large reasoning models (LRMs) improve task performance by generating longer intermediate reasoning traces, but this substantially increases inference costs and makes low-precision quantization increasingly important. However, aggressively …

Purpose: Surgical operative reports support procedural documentation, surgical training, performance assessment, and workflow review. However, extracting meaningful information often requires extensive manual review and clinical expertise.…

Loco-manipulation, which requires mobile manipulators to coordinate locomotion and manipulation over long horizons, is a key capability for large-object rearrangement in applications such as service robotics and warehouse automation. Despi…

Many multimodal alignment problems require mapping a source modality into a fixed space defined by a target modality, where the target space is not merely an intermediate embedding but is used directly for downstream analysis. In this sett…

Can a sender that only computes hashes, with a language model only at the receiver, transmit short human text more cheaply than a classical sender trained on the same domain? We answer with one pre-registered run on 1,000 English user utte…

In many areas of AI, general-purpose models have increasingly replaced handcrafted methods and specialized architectures. We argue that embodied AI is poised for a similar shift. Our key claim is that embodied tasks can be formulated as in…

This paper describes an approach and use case to estimate the correctness of LLM-generated COBOL summaries without access to human-authored references. The core intuition is that inter-model agreement on semantics is informative about trut…

The pigs were bleeding. That was the point of the experiment: could airway pressure reveal hemorrhage before it became critical? In the UCR Time Series Classification Archive, the de facto benchmark for Time Series Classification (TSC), th…

Radiology AI has developed along two paths: specialized models that perform well on narrow tasks but cover few clinical findings, and generalist models that address a broader range of tasks but remain prone to hallucination and inaccurate …

Reinforcement learning (RL) rewards are notoriously difficult to design and control, often leading to the model learning unintended behaviors such as reward hacking. One potential solution is to monitor for reward hacking and penalize it w…

The key-value (KV) cache dominates memory capacity and bandwidth in long-context LLM serving. While 4-bit microscaling formats (NVFP4, MXFP4) shrink the cache and run attention on FP4 Tensor Cores, a fundamental gap remains between algorit…

The timeline by which quantum computers can solve breakthrough problems in science depends on improved quantum algorithms as much as on better hardware. Such algorithmic advances are typically achieved through many years of expert human co…

Dominant methods for interpreting large models impose strong structural assumptions. Generative Latent Priors (GLP) are a complementary approach: a diffusion model that learns the distribution of a frozen model's activations directly, impo…

Machine learning (ML) methods have been explored as a means of optimizing lattice field theory calculations, with increasing interest in recent years. This chapter gives an introduction and summary to the use of ML methods to optimize latt…

Google DeepMind 发布新研究，展示 AI 智能体如何加速加密系统压力测试。在人类指导下，其模型发现了 legacy 1024-bit RSA 加密系统的两个重大弱点，研究详情由 VP Science Pushmeet 在引用帖中进一步解释。

研究团队推出 FoundationWorlds 框架，首个实例 ToyBlocks 是基于机械臂与桌面方块的开放仿真环境，可自动生成任务与演示数据，单块 GPU 并行执行数百个规划，最高达 24 倍实时速度。该环境支持域随机化与强化学习、运动规划生成技能，并用于训练 Molmo 2 高层推理模型与 ManiFlow 低层动作模型。

小红书智创 AIGC 团队提出 GlyphAnchor，用位置锚定字形先验为文生图和图像编辑模型补充显式字形与空间线索。在 FireRed-Image-Edit-1.1、Qwen-Image-Edit-2511 和 Z-Image 上，LongTextBench 中英文平均得分分别提升至 0.985、0.984 和 0.981。

Ai2 发布 ToyBlocks，一个围绕机械臂和桌面方块的开源仿真框架，作为其 FoundationWorld 框架的首个受控环境，用于研究机器人学习与评测。

Looping is a powerful inductive bias for reasoning. By repeatedly iterating a recurrent block, looped models can scale their effective depth and enable multi-step reasoning in latent space. However, existing looped models are not inherentl…

Instruction-tuned large language models (LLMs) answer at greater length than a request needs. We ask whether a training-free controller inside the decoding loop can remove that surplus while preserving content, judged against the simplest …

Multi-agent LLM systems increasingly aggregate judgments across model instances, but reasoning about other agents can itself introduce failure. We study a setting in which LLMs shift their public decisions after observing ambiguous social …

We present PhysioWave-T, a token-efficient wavelet foundation model family for EEG, ECG, and sEMG. Dynamic scale folding recombines J+1 wavelet subbands prior to tokenization, compressing sequence length from (J+1)CS to CS tokens for J lev…

Named entity recognition (NER) is challenging for social media data in a low-resource language. LLMs often lag behind pretrained language models (PLMs) in NER performance, but they show promise in handling cases that PLMs struggle with. Us…

Continuous music emotion recognition (MER) estimates how Arousal and Valence evolve within a song, yet the field's standard metric, pooled frame-level correlation, is dominated by between-song differences and cannot distinguish a model tha…

Weak supervisors are usually judged by their own errors, but what matters is what a student learns from them. For squared loss and any linear learner shared by all supervisors, we show that a supervisor's value is determined by its errors …

Translating parallel scientific codes between HPC programming frameworks is a critical but labor-intensive task. Existing LLM-based approaches rely on fixed sequential pipelines with undifferentiated repair strategies and correctness crite…

Frontier language models are increasingly deployed as agents, and how well an agent performs depends not only on its model but also on its harness: the prompts, tools, memory, and control loop through which the model acts. When an agent is…

The growing reliance on high-fidelity, state-of-the-art machine learning based models for engineering decision-making necessitates robust and systematic approaches for model selection. While high predictive accuracy at untrained points is …

Proximal Policy Optimization (PPO) stabilizes policy updates by clipping the importance ratio between the new policy and the data-collecting policy. The standard rule uses one fixed clipping range for all samples. While this choice offers …

Can frontier general-purpose agents understand client intent, explore creative directions, execute revisions, and prepare production deliverables? We introduce DRAFT-Bench (Design Reliability Across Feedback and Tasks), a lifecycle-oriente…

Probabilistic load forecasts for AI data centers need to represent both uncertainty under changing workloads and temporal dependence to support grid operations. This paper develops an open, grid-oriented benchmark using measured GPU power …

Quantization-aware training (QAT) is the most reliable way to obtain accurate low-bit large language models (LLMs), but training with AdamW keeps two dense FP32 states for every weight matrix. We find that low-rank memory-efficient optimiz…

Automated scientific discovery has the potential to advance understanding of disease mechanisms and accelerate identification of early disease markers. Manual data annotation is infeasible at population scale, motivating methods that autom…

Many professional reports reuse the structure of prior editions while updating the content. We formalize this setting as form-restricted report generation: given a sample report and new grounding documents, generate a report that preserves…

Real-world multivariate time series rarely come with verified ground-truth causal structure, so research on time-series causal discovery and treatment-effect estimation depends on synthetic data. Existing tools are either fixed datasets th…

We study the problem of causal effect identification from an arbitrary set of observational and/or interventional distributions, which we call Universal Identifiability (uID). The uID problem generalizes existing classical identifiability …

Recent progress in embodied robotics is bringing robots closer to deployment in homes, as vision-language models (VLMs) are demonstrating significant advances in reasoning, making VLM-driven robots promising home assistant agents. These ag…

Machine learning methods for solving partial differential equations (PDEs) significantly improve computational efficiency over traditional numerical solvers such as finite element method (FEM). However, PDE dynamics inherently span both lo…

Dwarkesh Patel 花费 20,000 美元 API 额度让多个 AI 模型在社交欺骗游戏 Blood on the Clocktower 中对弈，并上线了 benchmark 网站 clocktowerbench.com，也开放让人类与 AI 对玩。他观察到模型今年在临场策划、虚张声势和协作推理拆穿阴谋方面明显进步，并称 OpenAI 新模型在该游戏上明显强于 Anthropic。Noam Brown 转发表示对该评测方法印象深刻，并邀请 Dwarkesh 到 …