跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+1已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-07 18:29 · 全站最近入库：2026-11-07 17:43各信源进度 →

统计口径与数据新鲜度

统计 2026-11-06 18:59 — 2026-11-07 18:59（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-07 18:29最近发现新增版本：2026-11-07 17:43库内论文最新更新时间：2026-11-06 02:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

17,100 已收录论文14,661 AI 相关4,056 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 7 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-07 18:28（北京时间）
版本更新 · v2arXiv:2609.35670

Truthful-in-Expectation Mechanism with Constant Maximin-Share Guarantee

Mengfan Ma, Biaoshuai Tao, Fangxiao Wang

原文摘要

We study the truthful and fair allocation of $m$ indivisible goods to $n$ strategic agents with additive valuations. Babaioff, Feige, and Manaker Morag (FOCS~2026) gave a randomized mechanism that uses only the agents' rankings of the goods, is truthful-in-expectation (TIE), and guarantees every agent $1/(H_{n-1}+2)=Θ(1/\log n)$ of her maximin share (MMS) in every realized allocation, where $H_{n-1}$ is the $(n-1)$th harmonic number; this is nearly the best possible with rankings alone. They conjectured that cardinal information allows TIE mechanisms to achieve a constant ex-post MMS guarantee. We confirm this conjecture: our TIE mechanism gives every agent at least $1/6$ of her truncated proportional share (TPS), and hence of her MMS, in every realized allocation. Moreover, the mechanism is ex-ante envy-free and can be implemented in polynomial time as an explicit lottery over at most $m(n-1)+1$ allocations.

cs.GT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07953

A Behavioural Framework for Predicting and Understanding Loss of Control in Frontier Artificial Intelligence Systems

Yao Huang, Yichi Zhang, Yifan Wang, Yitong Sun, Haoyu Dong, Jifan Ma, Jinzhe Tu, Xiaojian Li 等 11 位作者

原文摘要

Frontier artificial intelligence (AI) systems are increasingly operating over longer horizons with diminishing human oversight, raising the risk of loss of control: systems acting beyond effective human control with potentially irreversible consequences. Because such failures may become observable only after containment is difficult, they must be assessed prospectively. We introduce a behavioural framework that decomposes loss-of-control risk into three factors: misaligned motive, harm-enabling capability, and monitoring evasion. We operationalise these factors through 13 measurable aspects and 29 evaluation tasks, whose scores are combined into a single loss-of-control (LoC) score. Across 13 frontier models, the LoC score shows strong prospective validity, correlating with failure rates in contained long-horizon risk scenarios (Pearson r = 0.84). Risk varies systematically across models and cannot be explained by capability alone. We further show that the framework can guide targeted mitigations: fine-tuning and monitoring directed at diagnosed vulnerabilities reduce failure rates while largely preserving general performance. These results provide a practical basis for predicting, understanding, and mitigating loss-of-control risk before it materialises.

cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07192

Backbone-Informed Adaptation after EEG Pretraining: A Capacity-Controlled Study

Mingyang Jiang, Yamin Li, Fan Ma, Daniel Moyer, Hua Xu, Catie Chang

原文摘要

Electroencephalography (EEG) foundation models learn representations that combine information across channels and time. This structure motivates adapters that model the same relationships during downstream learning. However, it is not clear whether such a design outperforms other candidate adapters. Moreover, in order to arrive at a fair comparison between candidate adapters, we also need to consider their trainable parameters. Here, we ask whether a backbone-informed (native) adapter makes better use of a given capacity by comparing it against a token-wise multilayer perceptron control that transforms each feature vector independently. We approximately match their trainable parameter counts and keep the pretrained encoder fixed. Across two EEG foundation models and tasks covering emotion recognition, sleep staging, and EEG event classification, the native adapter shows no consistent advantage. For one backbone, differences between the designs are small relative to variation across runs. For the other, the token-wise control performs better on emotion recognition and EEG event classification. On sleep staging, the native adapter's advantage over the token-wise control is reduced when we also train the component that processes sequences of EEG segments. The relative performance of the two adapters depends on the backbone, task, and downstream training protocol. These findings motivate evaluating backbone-informed adapters against capacity-matched alternatives.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06097

Two-Sided Screening in Quality-Differentiated Markets

Yaohao Liu, Mengfan Ma, Mingyu Xiao

原文摘要

Motivated by digital marketplaces such as Uber and Airbnb, we study how a two-sided platform designs a menu of qualities, consumer prices, and provider wages. Consumers and providers self-select according to their private values and costs, so the platform must design its menu to attract consumers while inducing enough supply to meet their demand. We study this coordination problem over a continuous quality space, requiring supply to cover demand at every quality threshold. We formulate menu design as an optimization over trading distributions, which specify how much trade occurs at or above each quality. Through convexification of the technological cost function, we characterize the profit- and welfare-optimal trading distributions. This characterization shows how production technology alone can reduce menu size without sacrificing optimal profit or welfare, regardless of the type distributions, and determines when optimal menus can be finite. We then show that profit maximization can be highly efficient: under monotone hazard rate conditions on both sides, a profit-optimal menu achieves at least $1/(e-1)$ of optimal social welfare. We next consider the practical setting in which the menu size is restricted to a prescribed number of offers. We establish how the restricted menu approximates the unrestricted optimum in profit. We develop an algorithm that computes a menu within this size limit in polynomial time. The computed menu simultaneously approximates the unrestricted optimal profit and social welfare with additive error.

cs.GT

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2511.20836

Structured Prompts Improve Evaluation of Language Models

Asad Aali, Muhammad Ahmed Mohsin, Vasiliki Bikia, Arnav Singhvi, Richard Gaus, Suhana Bedi, Hejie Cui, Miguel Fuentes 等 18 位作者

原文摘要

As language models (LMs) are increasingly adopted across domains, high-quality benchmarking frameworks are essential for guiding deployment decisions. However, frameworks such as Holistic Evaluation of Language Models (HELM) typically evaluate models under a single static prompt configuration, even though model behavior depends strongly on prompt choice. As a result, reported scores can reflect prompt choice as much as model capability. Declarative prompting frameworks, such as DSPy, offer a scalable way to operationalize this evaluation protocol by evaluating models under structured prompting strategies rather than static prompts. Here, we conduct a reproducible DSPy+HELM benchmarking study and quantify how prompt choice impacts benchmark outcomes. Using five prompting methods, we evaluate four frontier and two open-source LMs across seven benchmarks against HELM baseline scores and find that prompt choice can materially impact leaderboards. Structured prompting improves performance (by 6% on average), alters comparisons (leaderboard rankings shift on $5/7$ benchmarks); chain-of-thought provides the strongest cost-performance tradeoff while more advanced optimizers offer smaller additional gains. Beyond the known intuition that prompts affect outputs, our benchmarking study integrates structured prompting into an established evaluation framework and quantifies how prompt choice alone impacts leaderboards. We open-source (i) DSPy+HELM Evaluation (https://github.com/stanford-crfm/helm/pull/3893) and (ii) Prompt Optimization Pipeline (https://github.com/StanfordMIMI/dspy-helm).

cs.CL · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.01999

Optimal Online Learning in Bilateral Trade Through Interest

Mengfan Ma, Haoyu Song, Yiran Tong

原文摘要

We consider online learning in bilateral trade on platforms such as Uber, Airbnb, and eBay. In each round, a platform posts a payment to a seller and a price to a buyer, both with private valuations, and observes only whether trade occurs. Its objective is to maximize cumulative gains-from-trade, the sum of the differences between buyers' and sellers' valuations across completed trades. We measure the platform's performance by its regret against the best fixed common price. Financial self-sufficiency motivates global budget balance (Bernasconi et al., 2024), which allows profits from some trades to subsidize others, provided that the final balance is nonnegative. Such financial planning should also account for the time value of money: profits earned earlier can accumulate interest, providing additional funds for future subsidies. Motivated by this observation, we introduce global budget balance with interest, under which a platform starting with no funds can use both trading profits and accrued interest to finance subsidies. For a horizon of $T$ rounds and a fixed exponent $θ\ge0$, we consider the per-round interest rate $r_T = T^{-θ}$. We study two classic valuation models, adversarial and correlated i.i.d., and obtain tight bounds on regret against the best fixed common price in both. As the interest rate grows, optimal regret in each model drops from $\tildeΘ(T^{3/4})$ to $\tildeΘ(T^{5/7})$. The intermediate rates differ: $\tildeΘ(T^{3θ/4})$ for adversarial valuations when $20/21 < θ< 1$, and $\tildeΘ(T^{(2θ+3)/7})$ for correlated i.i.d. valuations when $1 < θ< 9/8$. Finally, as an extension, we study $α$-regret, with approximation factor $α\ge1$, for adversarial valuations against the best feasible distribution over price pairs, and show that the optimal competitive ratio rises from 2 to 3 as interest strengthens.

cs.GT

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.27982

ViP-Rig: Visual-Prompted Controllable Rigging

Zihan Qin, Mingze Sun, Yifan Mao, Jialei Xu, Jingfeng Guo, Changrong Hu, Wenbo Zhao, Junjun Jiang 等 9 位作者

原文摘要

Rigging is inherently task-dependent because the same mesh may require different skeletons and deformation behaviors across animation tasks. In practice, artists often inspect an initial rig and repeatedly edit its skeletal structure and deformation behavior to meet specific animation requirements. Existing automatic methods primarily generate a plausible rig from geometry, offering limited explicit control over the resulting skeleton and deformation behavior. In this work, we present ViP-Rig, a visual-prompted framework that supports both prompt-first rigging and result-guided editing by injecting features extracted from user-drawn or edited 2D skeletal and rigidity prompts into frozen pretrained backbones. Specifically, ViP-Rig consists of two stages, Skeleton Generation and Skinning Prediction. In the first stage, the skeletal sketch is processed by the Dense-to-Compact Visual Prompt Encoding to produce compact, fixed-length conditioning tokens. The resulting tokens are injected into a frozen pretrained autoregressive generator through gated adapters to control joint placement and branching structure while preserving the generator's geometric prior. In the second stage, the rigidity map is processed using the same visual encoding design, while the pretrained skinning backbone remains frozen. The resulting tokens are symmetrically injected into the point and joint streams to modulate point-joint compatibility and the resulting skinning weights. Experiments on Articulation-XL2.0 and zero-shot evaluation on ModelsResource show that ViP-Rig more accurately recovers target skeletons and skinning weights than geometry-conditioned baselines under prompt-guided evaluation. Qualitative results further demonstrate explicit and localized control in both prompt-first rigging and result-guided editing.

cs.CV

查看论文
arXiv ↗PDF ↗