虚拟人设能否预测真实受众反应？研究揭示无角色基线反超人设模拟
当前营销领域常使用大语言模型构建“虚拟人设”以预测真实受众对文案的反应。本研究基于Upworthy研究档案中数千次真实流量点击率A/B测试作为基准，开展了从模拟到真实的有效性检验。实验对比了基于真实人口统计特征构建的10人虚拟人设面板与无角色设定的基准模型，结果显示，无角色基准在文案效果模拟上的表现反而击败了基于人设的模拟，对当前AI受众模拟的有效性提出了质疑。
DC AI 热点
全部 AI 动态
9月24日2026-09-24
现有预条件器能否改善生物医学表格基座学习？TabPFN优化实证研究
针对结构化生物医学数据分析，表格基座模型展现出巨大潜力，其中TabPFN在小样本表格分类任务中表现尤为突出。然而，优化和预条件策略对生物医学场景微调的影响尚缺乏研究。本文对TabPFN v2.5展开系统性实证评估，在涵盖阿尔茨海默病、乳腺癌、精神分裂症等疾病及KEEL库的59个生物医学数据集上，测试了五种基于AdamW的预条件策略，为优化生物医学表格基座模型微调提供了实验参考。
4DGS-JEPA：面向动态高斯泼溅的时序组合联合嵌入预测架构
动态高斯泼溅能显式表征随时间演化的3D场景，但现有方法多针对重建、未来状态生成或渲染进行优化，缺乏对可复用预测动力学的学习。对此，研究人员提出了 4DGS-JEPA，一种用于动态高斯场景因果多时域预测的原生联合嵌入预测架构。该模型构建了涵盖场景级、运动群级及高斯级的层次化表征，并结合时域条件转移算子，能够同时支持直接预测与递归推演。
基于超图神经网络的胶质母细胞瘤生存期精准与可解释预测研究
针对多形性胶质母细胞瘤（GBM）生存预测对高准确度和透明度的双重需求，研究人员指出现有方法往往在性能与可解释性间妥协，且过度依赖单一成像模态，未能充分利用互补信息。该研究提出一种超图神经网络方案，认为这两者并非固有冲突，旨在利用图神经网络的结构优势，在保证强判别能力的同时提取具解释性的特征表征，以提升多模态临床预测能力（原文摘要截断）。
Ovis-Embedding：拓展通用全模态嵌入模型前沿
该研究推出了全模态嵌入模型家族 Ovis-Embedding，实现对文本、图像、视频和音频的原生整合。不同于将各个独立的模态塔简单组合，Ovis-Embedding 采用共享的多模态骨干网络，将不同模态编码至统一的表征空间中。该模型以预训练的 Qwen-omni 为骨干网络，通过低秩初始化的对比训练完成适配，并引入了以数据为中心的全模态训练策略。
X-Planner：面向具身智能的事件结构化任务规划框架
针对现代视觉-语言-动作（VLA）系统在长程操作中缺乏显式中间结构、现有思维链规划器依赖粗粒度标注的问题，研究团队提出了 X-Planner 规划前端。该方案同时改善具身推理的监督与表征，融合了第一人称视角、通用操作接口及遥操作等多源数据，构建了具备分层粒度和差异化标注深度的规划数据集。由于原始摘要截断，具体的下游控制效果待全文进一步阐释。
Lean Pool：由AI智能体自主维护与优化的形式化数学代码库
Lean Pool 是一个形式化数学代码库，其核心特色在于完全由 AI 智能体负责拓展、维护与持续优化。该项目展示了人工智能在形式化定理证明与复杂数学知识归档中的自主管理潜力，有助于提高数学形式化库的组织效率与代码质量。由于原论文摘要提供的信息极为简略，具体的智能体协作机制与工程实现细节仍有待进一步公开。
AI神经科学家：面向神经影像分析的交互式智能体界面
神经影像数据分析通常需要专业的编程与统计技能，这给非计算背景的研究人员带来了门槛。为此，研究团队推出了“AI神经科学家”，这是一种用于交互式数据探索的语言智能体。该系统将大语言模型与神经影像专业工具集相结合，支持研究人员直接通过自然语言查询数据质量、执行建模与可视化并设定分析参数，为小规模数据探索提供了一种替代传统脚本处理流程的透明且交互式的解决方案。
MedGate-Fusion：融合初诊文本与生理指标的脑卒中风险分层模型
针对基层医疗中早期卒中风险信号分散于常规指标与非结构化临床文本的难题，研究人员提出了多模态门控架构 MedGate-Fusion。该模型通过 Transformer 提取患者初次就诊叙述的语义嵌入，并与 10 项常规生理风险标志物进行多模态融合。研究基于加拿大基层医疗监测网络（CPCSSN）的电子病历数据，构建了包含超 10 万名患者的初诊队列，旨在实现前瞻性卒中风险分层。
When LLM Agents Fail to Read the Room: ReAdapt for Relational Social Reasoning
arXiv:2609.25284v1 Announce Type: new Abstract: A social agent's most basic decisions (should I react to this post? who should I reach out to?) are not purely content problems. The right action often hinges on the latent relationship between people -- tie strength, reciprocity, mutual connections -- rather than on which content is most salient. Standard LLM agent loops do not explicitly represent how new relational evidence should revise the agent's current social hypothesis, leaving them prone to surface-obvious choices when relational and content cues diverge. We formalize this failure mode with a relationship-reasoning benchmark: 500 synth
Attention as a Routing Graph: Live Circuit Extraction from a Single Forward Pass
arXiv:2609.25285v1 Announce Type: new Abstract: Finding circuits in language models usually means running many careful interventions. We try something simpler: treat attention as a routing map from one forward pass, keep a small set of routes that point toward the answer, and ask whether those routes actually matter. They often do. On induction and IOI (tasks where the "right" circuit is already known), ablating our extracted edges hurts the model much more than ablating a random set of the same size. We evaluate n=100 prompts per cell on GPT-2 Small, GPT-2 Medium, and Pythia-410M, with paired gap tests and bootstrap confidence intervals. The
Learned Enterprise Data Comprehension: Compression and Routing for Data Agents
arXiv:2609.25286v1 Announce Type: new Abstract: Structured-data agents in enterprise settings must reason over complex data environments whose relevant evidence is distributed across schemas, relationships, policies, and recurring business roles. Modern agentic systems often address this burden through reusable markdown-style memory or skill files that preserve previously discovered information for later queries, reducing the need to rediscover the same structure repeatedly. This is useful, but it obscures a natural division of labor: agents are well suited to semantic reasoning, while learned systems are well suited to predicting and organiz
Making Agents More Consistent: Skills Should Form Habits for Repeat Tasks
arXiv:2609.25299v1 Announce Type: new Abstract: On repeated work, agents are inconsistent. We ran 42 tasks three times each and found that, depending on the model, 38% to 74% returned answers that did not agree. Consistency is what a buyer, an auditor, or a regulator requires, and agents do not have it. They are wasteful too: 95.3% to 97.2% of what an agent generates goes to re-deriving a plan the system already knows. We propose skill habit formation. An agent mines its own execution history for candidate skills, deterministic variants that compete against the incumbent rather than replacing it. A candidate declares the region of input space
Potential for Enhanced Learning in Machine Learning Classes by Using Wiki LLM Indexing
arXiv:2609.25303v1 Announce Type: new Abstract: Large language models are increasingly deployed as course-specific tutors, but their usefulness depends on grounding in vetted instructional materials that are often revised mid-semester. Our prior work built a multimodal retrieval-augmented generation (RAG) system over an authentic machine learning course corpus (Foundations of Machine Learning) and found that retrieval improved contextual grounding, but that fixed retrieval strategies were suboptimal. That motivates a different question: whether how a corpus is structured at ingest time matters more than how much is retrieved at query time. We
Clarification Is Not Correction: LLMs Fail to Let Go
arXiv:2609.25337v1 Announce Type: new Abstract: Dialogue failures in language models are usually framed as memory failures: context too long, summaries lossy, a constraint forgotten. We argue this misses a deeper problem: in many conversations the model does not forget, it commits too early. An ambiguous early turn collapses into a single hidden interpretation, and later clarification is filtered through that commitment. We call this early posterior collapse: unresolved user intent collapsing into a committed task state before ambiguity is resolved. We study it with controlled dialogue tasks in writing, planning, and coding using Gemini-2.5-P
From Decorative to Load-Bearing: Task Difficulty Shapes the Causal Role of Chain-of-Thought
arXiv:2609.25366v1 Announce Type: new Abstract: Chain-of-thought (CoT) monitoring is only meaningful if written reasoning causally constrains the answer. We introduce continuation-based causal testing, an ablation-patch intervention that perturbs one reasoning step, truncates the chain, and forces the model to continue from the corrupted prefix. It measures how load-bearing a CoT is for the final answer, a behavioral notion distinct from mechanistic faithfulness. Across Gemma-2-9B-IT, Llama-3.1-8B-Instruct, and DeepSeek-R1-Distill-Qwen-7B on GSM8K, MMLU, and BIG-Bench Hard, CoT load-bearingness tracks model-relative task difficulty: on easy t
Robust Failure, Conservative Repair: Textual Knowledge Distillation from Cross-Model Failures
arXiv:2609.25400v1 Announce Type: new Abstract: Failure-based textual knowledge distillation aims to discover gaps in a model's knowledge by examining its task errors. The distilled knowledge can be useful for the reasoning of both this model ("source model") and other models. However, this transfer of knowledge may not be stable. We define a rule atom to be a standalone rule injected into a model's textual input at inference time. A rule atom can encode transferable task knowledge or model-specific reasoning patches that can confuse other models. Also, the injected rule atoms can be misapplied to unrelated cases, causing the model to incorre
Efficient Iterative Retrieval with Heterogeneous Batching
arXiv:2609.25405v1 Announce Type: new Abstract: Modern information retrieval increasingly employs both embedding and generative models to handle complex queries. However, current serving systems suffer from low throughput and poor GPU utilization because they execute these models in isolation. Coarse-grained partitioning, such as dedicating GPUs to specific tasks, fails to adapt to dynamic workloads and creates computational "bubbles". To address these, we present Orthrus, a serving system that performs heterogeneous batching within a unified inference loop. The primary challenge lies in unifying embedding and generation workloads with confli
From Offline Proxies to Online Decisions: A Layered Engagement Evaluation Framework for Conversational AI
arXiv:2609.25408v1 Announce Type: new Abstract: Online A/B experiments are the decision standard for user engagement, but traffic and readout time limit how many conversational-AI changes can be tested. We ask whether an offline signal designed to be computable without treatment-arm user exposure agrees with the outcomes of those experiments. We contribute a reusable construction and diagnosis checklist that treats an offline proxy as a chain of three alignments: behavioral label to product outcome, learned classifier to candidate-assistant behavior, and aggregated offline signal to experiment effect. A companion evaluation protocol audits th
ZeroGate: Trust-Preserving Fast Paths for Governed AI Agent Runtimes
arXiv:2609.25443v1 Announce Type: new Abstract: Moving authorization earlier can shorten an agent's dispatch boundary without removing authorization work. It can also admit an action whose payload, authority, or relevant state has changed. ZeroGate separates exact-action approval from durable local admission: an issuer signs a short-lived ActionPass, and a trusted runtime adapter reconstructs the final action before a local gate checks its binding and consumes its nonce. A SQLite transaction couples nonce consumption, applicable quota updates, and an admission receipt. We state a conditional decision-preservation proposition: successful local
Rollout Efficiency in Reinforcement Learning for Reasoning Large Language Models: A Taxonomy and Future Directions
arXiv:2609.25463v1 Announce Type: new Abstract: Reasoning-oriented reinforcement learning enables large language models to solve mathematical, coding, and other multi-step tasks, but shifts a substantial portion of the training cost to rollout, where trajectories are generated for policy updates. Efficient rollout mechanisms are therefore essential to reduce this cost while maintaining the freshness, consistency, and statistical validity of training data. This survey provides a systematic taxonomy of recent research on rollout efficiency for reasoning-oriented reinforcement learning, classifying existing approaches from both mechanism and bot
Real-Time Hand Gesture Recognition for OpenXR Using Transformer-Based Machine Learning
arXiv:2609.25466v1 Announce Type: new Abstract: Hand gesture recognition is a key component in human-computer interaction (HCI), enabling intuitive interfaces for applications in gaming, virtual reality (VR), robotics, and more. This study integrates transformer-based machine-learning models for real-time hand gesture recognition, using hand-tracking data captured through the OpenXR standard in Unity. We leverage positional data of hand joints and wrist rotation angles to train a custom gesture recognition system. By utilizing the sequential modeling capabilities of transformers, the system captures temporal dependencies within short gesture
ShowTellArena: Evaluating Business Workflow Understanding from Demonstrations
arXiv:2609.25467v1 Announce Type: new Abstract: We often teach a colleague by showing the work and explaining the decisions as we go. How can we check what an agent understood from the same lesson? We introduce ShowTellArena, a benchmark protocol and public dataset for comprehension after narrated business demonstrations. The v1.0 release contains 50 business workflow tasks, with recordings, screenshots, narration, fixture seeds, and 502 questions. Tasks span finance, hiring, procurement, customer decisions, inventory, and logistics. The protocol holds the business scenario and quiz fixed while allowing each product to capture the lesson thro
RAG-NAROK: Retrieval-Aware Knowledge Corpus Poisoning in RAG with Source-specific Refutation
arXiv:2609.25469v1 Announce Type: new Abstract: Retrieval augmented generation (RAG) systems have emerged as the dominant architecture for grounding large language model (LLM) outputs in verifiable external knowledge, yet their structural reliance on a dynamic retrieval pipeline introduces a largely unexplored class of adversarial vulnerability. Existing knowledge-base poisoning attacks are fundamentally static. Adversarial documents are pre-computed and injected without any awareness of what the victim system will actually retrieve for a given query, leaving the attack blind to the competitive documentary landscape that surrounds its payload
Spectra: A Rules-Driven LLM Pipeline for Automated KYC Document Processing
arXiv:2609.25474v1 Announce Type: new Abstract: Know Your Client (KYC) onboarding in capital markets requires analysts to manually classify documents, extract structured data from heterogeneous sources, and validate compliance against complex regulatory policies. This process requires significant analyst time per client, with end-to-end onboarding often stretching to multiple weeks due to sequential handoffs. In this work, we analyze an on-boarding process and find that it comprises repeatable components well-suited to AI automation. We therefore propose a restructured workflow to be amenable to automation: we consolidate the traditional four
Queer inclusion in speech datasets: An audit and taxonomy of practical tensions
arXiv:2609.25491v1 Announce Type: new Abstract: In this paper, we examine speech datasets for their inclusion of LGBTQIA+, or queer, voices and provide a taxonomy of tensions to better understand why there is a lack of such voices in current speech technology datasets. Through an audit of six diverse speech datasets, we find that measurable queer representation is low (0-1.4% of speakers) - insufficient for robust disparity measurement. We take this community as a case study to consider what challenges and tensions are associated with collecting speech data from marginalized communities. For comparison, we audit an additional two datasets fro
Towards participatory speech dataset curation: A queer case study and conceptual framework
arXiv:2609.25496v1 Announce Type: new Abstract: In this paper, we motivate the need for a participatory speech dataset creation framework through a case study of the LGBTQIA+, or queer, community - a community with documented concerns about AI and reported harms, including attempts to develop 'gaydar' technologies that purportedly identify individuals as queer. We review common speech data collection practices, why these methods may be unsuitable for engaging with queer speakers, and discuss previous efforts in participatory AI with queer community engagement, as well as participatory endeavours specific to speech data collection for other ma
SMTB: Fast Structure-Mapping with Tight Bounds
arXiv:2609.25508v1 Announce Type: new Abstract: Structure-mapping forms analogies by aligning systems of relationally connected elements based on shared structure instead of surface features. We introduce a new structure-mapping algorithm: Structure-Mapping with Tight Bounds (SMTB) that is 5--15x faster than the structure-mapping engine (SME) and about 50\% better at finding mappings in large nested domains. SMTB is part of the broader Cognitive Rule Engine (CRE) project, a flexible multi-language-compatible framework with an accessible Python interface to state-of-the-art C++ implementations of core algorithms commonly used in cognitive syst
Weakly Supervised Quantum Error Mitigation
arXiv:2609.25555v1 Announce Type: new Abstract: Supervised approaches to quantum error mitigation learn a map from noisy circuit outputs to ideal ones, and therefore require the ideal outputs. Producing those ideal outputs demands noiseless classical simulation, whose cost grows exponentially with system size, so supervision is unavailable in exactly the regime where mitigation matters most. We ask whether cheap, individually unreliable signals drawn from circuit structure and hardware calibration can take the place of ideal labels. We assemble sixteen heuristic labeling functions (stabilizer and parity constraints, relaxation and readout cha
Recovering Agentic Sovereignty: Mitigating the Consensus Paradox via Contrastive Epistemic Decoding
arXiv:2609.25570v1 Announce Type: new Abstract: Large language models (LLMs) exhibit a parametric vulnerability to adversarial swarm consensus. To mitigate this sycophancy, we introduce Contrastive Epistemic Decoding (CED), a zero-shot inference intervention. Unlike standard Contrastive Decoding (CD) which relies on a weaker secondary model, CED utilizes a dual forward-pass on a single architecture to isolate conformity bias. By introducing a novel asymmetric, zero-bounded probability clamp and discrete top-k truncation mask, CED mathematically suppresses toxic consensus tokens without causing grammatical collapse. Evaluated across 7,200 pair
1 / 2下一页 →