主题图谱 / computation and language cs.cl

computation and language cs.cl

GeneTech 知识引擎共收录 112 篇相关科研实体，横跨 16 个垂直领域。数据来自 OpenAlex、arXiv、Crossref、PubMed、Europe PMC 等公开学术源，全部可溯源到原文。

年度产出趋势

代表性文献（按质量分排序，前 60 条）

• Diff Mining: Logit Differences Reveal Finetuning Objectives
  2026 · AI Agent 生态 · Finetuning has become the gold standard for refining existing behaviors and inducing new ones in language models, yet it often remains unclear exactly which behaviors emerge during this process. As models grow ever more …
• Decoupling Planning and Control for Instructable Agents
  2026 · AI Agent 生态 · Recent work shows that pre-trained, instruction-tuned vision-language models (VLMs) perform well at mapping from instructions and observations to high-level plans, but struggle to realize such plans as reliable low-laten…
• LLM Agents Perform Controlled Experiments Using Simulation Models
  2026 · AI Agent 生态 · Large language models (LLMs) have shown strong capabilities in reasoning, planning, and tool use, but many scientific and engineering tasks require more than plausible text and code generation. They require understanding…
• Expected Reward Prediction, with Applications to Model Routing
  2026 · AI 安全与对齐 · Reward models are a standard tool to score responses from LLMs. Reward models are built to rank responses to a fixed prompt sampled from a single model, for example to choose the best of n sampled responses. In this pape…
• Diff Mining: Logit Differences Reveal Finetuning Objectives
  2026 · AI 驱动科学发现 · Finetuning has become the gold standard for refining existing behaviors and inducing new ones in language models, yet it often remains unclear exactly which behaviors emerge during this process. As models grow ever more …
• FIRSTPASS: A Multi-Domain, Multi-Round Peer Review Dataset Grounded in Real Editorial Outcomes
  2026 · AI 驱动科学发现 · Scientific peer review datasets have trained AI systems exclusively on Computer Science and Machine Learning venues, producing models that critique ablation studies yet have never seen a biology reviewer demand contamina…
• Redakto - The Incognito Tab for LLMs
  2026 · 医疗人工智能 · Large Language Models (LLMs) are being increasingly used in everyday applications. A major challenge in the context of LLMs or Artificial Intelligence (AI) in general is to ensure privacy when using them, meaning that pe…
• An Approach to Simultaneous Acquisition of Real-Time MRI Video, EEG, and Surface EMG for Articulatory, Brain, and Muscle Activity During Speech Production
  2026 · 仿生智能 · Speech production is a complex process spanning neural planning, motor control, muscle activation, and articulatory kinematics. While the acoustic speech signal is the most accessible product of the speech production act…
• RAG-based EEG-to-Text Translation Using Deep Learning and LLMs
  2026 · 仿生智能 · The decoding of linguistic information from electroencephalography (EEG) signals remains an extremely challenging problem in brain-computer interface (BCI) research. In particular, sentence-level decoding from EEG is dif…
• FIRSTPASS: A Multi-Domain, Multi-Round Peer Review Dataset Grounded in Real Editorial Outcomes
  2026 · 脑科学 · Scientific peer review datasets have trained AI systems exclusively on Computer Science and Machine Learning venues, producing models that critique ablation studies yet have never seen a biology reviewer demand contamina…
• MerNav: A Highly Generalizable Memory-Execute-Review Framework for Zero-Shot Object Goal Navigation
  2026 · 具身智能 · Visual Language Navigation (VLN) is one of the fundamental capabilities for embodied intelligence and a critical challenge that urgently needs to be addressed. However, existing methods are still unsatisfactory in terms …
• Decoupling Planning and Control for Instructable Agents
  2026 · 具身智能 · Recent work shows that pre-trained, instruction-tuned vision-language models (VLMs) perform well at mapping from instructions and observations to high-level plans, but struggle to realize such plans as reliable low-laten…
• FedMental: Evaluating Federated Learning for Mental Health Detection from Social Media Data
  2026 · 隐私计算与数据要素 · Social media text data are often used to train Machine Learning (ML) models to identify users exhibiting high-risk mental health behaviors. However, sharing this sensitive data poses privacy risks and limits the growth o…
• Memorization Is Not Extraction: Tight Differential-Privacy Bounds and Audit Blind Spots
  2026 · 隐私计算与数据要素 · Memorization in large language models is measured through a zoo of definitions whose formal relations are unknown, and differential privacy (DP) is treated as a proxy against all of them at once. We pin down the exact DP…
• OceanGym: A Benchmark Environment for Underwater Embodied Agents
  2025 · AI Agent 生态 · We introduce OceanGym, the first comprehensive benchmark for ocean underwater embodied agents, designed to advance AI in one of the most demanding real-world environments. Unlike terrestrial or aerial domains, underwater…
• ContestTrade: A Multi-Agent Trading System Based on Internal Contest Mechanism
  2025 · AI Agent 生态 · In financial trading, large language model (LLM)-based agents demonstrate significant potential, but their decisions can be sensitive to noisy and non-stationary market information. We propose ContestTrade, a multi-agent…
• RAPID: Retrieval-Augmented Parallel Inference Drafting for Text-Based Video Event Retrieval
  2025 · AI 安全与对齐 · Retrieving events from videos using text queries has become increasingly challenging due to the rapid growth of multimedia content. Existing methods for text-based video event retrieval often focus heavily on object-leve…
• Smoothed Embeddings for Robust Language Models
  2025 · AI 安全与对齐 · Improving the safety and reliability of large language models (LLMs) is a crucial aspect of realizing trustworthy AI systems. Although alignment methods aim to suppress harmful content generation, LLMs are often still vu…
• TCUQ: Single-Pass Uncertainty Quantification from Temporal Consistency with Streaming Conformal Calibration for TinyML
  2025 · 边缘智能 · We introduce TCUQ, a single pass, label free uncertainty monitor for streaming TinyML that converts short horizon temporal consistency captured via lightweight signals on posteriors and features into a calibrated risk sc…
• HyCodePolicy: Hybrid Language Controllers for Multimodal Monitoring and Decision in Embodied Agents
  2025 · 具身智能 · Recent advances in multimodal large language models (MLLMs) have enabled richer perceptual grounding for code policy generation in embodied agents. However, most existing systems lack effective mechanisms to adaptively m…
• NavSpace: How Navigation Agents Follow Spatial Intelligence Instructions
  2025 · 具身智能 · Instruction-following navigation is a key step toward embodied intelligence. Prior benchmarks mainly focus on semantic understanding but overlook systematically evaluating navigation agents' spatial perception and reason…
• Rethinking the Embodied Gap in Vision-and-Language Navigation: A Holistic Study of Physical and Visual Disparities
  2025 · 具身智能 · Recent Vision-and-Language Navigation (VLN) advancements are promising, but their idealized assumptions about robot movement and control fail to reflect physically embodied deployment challenges. To bridge this gap, we i…
• Does the Appearance of Autonomous Conversational Robots Affect User Spoken Behaviors in Real-World Conference Interactions?
  2025 · 具身智能 · We investigate the impact of robot appearance on users' spoken behavior during real-world interactions by comparing a human-like android, ERICA, with a less anthropomorphic humanoid, TELECO. Analyzing data from 42 partic…
• A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges
  2025 · 具身智能 · Large vision-language models (VLMs) have evolved rapidly from contrastive image-text encoders and adapter-based assistants into natively multimodal foundation models that support long-context reasoning, agentic workflows…
• CLUES: Collaborative High-Quality Data Selection for LLMs via Training Dynamics
  2025 · 隐私计算与数据要素 · Recent research has highlighted the importance of data quality in scaling large language models (LLMs). However, automated data quality control faces unique challenges in collaborative settings where sharing is not allow…
• Simple Yet Effective: Extracting Private Data Across Clients in Federated Fine-Tuning of Large Language Models
  2025 · 隐私计算与数据要素 · Federated large language models (FedLLMs) enable cross-silo collaborative training among institutions while preserving data locality, making them appealing for privacy-sensitive domains such as law, finance, and healthca…
• Leveraging ASIC AI Chips for Homomorphic Encryption
  2025 · 隐私计算与数据要素 · Homomorphic Encryption (HE) provides strong data privacy for cloud services but at the cost of prohibitive computational overhead. While GPUs have emerged as a practical platform for accelerating HE, there remains an ord…
• Anti-adversarial Learning: Desensitizing Prompts for Large Language Models
  2025 · 隐私计算与数据要素 · With the widespread use of LLMs, preserving privacy in user prompts has become crucial, as prompts risk exposing privacy and sensitive data to the cloud LLMs. Traditional techniques like homomorphic encryption, secure mu…
• Leveraging Multi-Agent System (MAS) and Fine-Tuned Small Language Models (SLMs) for Automated Telecom Network Troubleshooting
  2025 · 6G 与卫星互联网 · Telecom networks are rapidly growing in scale and complexity, making effective management, operation, and optimization increasingly challenging. Although Artificial Intelligence (AI) has been applied to many telecom task…
• BenCao: An Instruction-Tuned Large Language Model for Traditional Chinese Medicine
  2025 · 中医药工具 · Traditional Chinese Medicine (TCM), with a history spanning over two millennia, plays a role in global healthcare. However, applying large language models (LLMs) to TCM remains challenging due to its reliance on holistic…
• Can Models Learn Skill Composition from Examples?
  2024 · AI 安全与对齐 · As large language models (LLMs) become increasingly advanced, their ability to exhibit compositional generalization -- the capacity to combine learned skills in novel ways not encountered during training -- has garnered …
• Geometric-Averaged Preference Optimization for Soft Preference Labels
  2024 · AI 安全与对齐 · Many algorithms for aligning LLMs with human preferences assume that human preferences are binary and deterministic. However, human preferences can vary across individuals, and therefore should be represented distributio…
• Failures to Find Transferable Image Jailbreaks Between Vision-Language Models
  2024 · AI 安全与对齐 · The integration of new modalities into frontier AI systems offers exciting capabilities, but also increases the possibility such systems can be adversarially manipulated in undesirable ways. In this work, we focus on a p…
• Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision
  2024 · AI 安全与对齐 · Current AI alignment methodologies rely on human-provided demonstrations or judgments, and the learned capabilities of AI systems would be upper-bounded by human capabilities as a result. This raises a challenging resear…
• What are human values, and how do we align AI to them?
  2024 · AI 安全与对齐 · There is an emerging consensus that we need to align AI systems with human values (Gabriel, 2020; Ji et al., 2024), but it remains unclear how to apply this to language models in practice. We split the problem of "aligni…
• ChatGPT Rates Natural Language Explanation Quality Like Humans: But on Which Scales?
  2024 · AI 安全与对齐 · As AI becomes more integral in our lives, the need for transparency and responsibility grows. While natural language explanations (NLEs) are vital for clarifying the reasoning behind AI decisions, evaluating them through…
• When Raw Data Prevails: Are Large Language Model Embeddings Effective in Numerical Data Representation for Medical Machine Learning Applications?
  2024 · 医疗人工智能 · The introduction of Large Language Models (LLMs) has advanced data representation and analysis, bringing significant progress in their use for medical questions and answering. Despite these advancements, integrating tabu…
• Self-supervised Speech Models for Word-Level Stuttered Speech Detection
  2024 · 医疗人工智能 · Clinical diagnosis of stuttering requires an assessment by a licensed speech-language pathologist. However, this process is time-consuming and requires clinicians with training and experience in stuttering and fluency di…
• A review on the use of large language models as virtual tutors
  2024 · 边缘智能 · Transformer architectures contribute to managing long-term dependencies for Natural Language Processing, representing one of the most recent changes in the field. These architectures are the basis of the innovative, cutt…
• Transforming Surgical Interventions with Embodied Intelligence for Ultrasound Robotics
  2024 · 具身智能 · Ultrasonography has revolutionized non-invasive diagnostic methodologies, significantly enhancing patient outcomes across various medical domains. Despite its advancements, integrating ultrasound technology with robotic …
• EmbSpatial-Bench: Benchmarking Spatial Understanding for Embodied Tasks with Large Vision-Language Models
  2024 · 具身智能 · The recent rapid development of Large Vision-Language Models (LVLMs) has indicated their potential for embodied tasks.However, the critical skill of spatial understanding in embodied environments has not been thoroughly …
• OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents
  2024 · 具身智能 · This paper presents OmniJARVIS, a novel Vision-Language-Action (VLA) model for open-world instruction-following agents in Minecraft. Compared to prior works that either emit textual goals to separate controllers or produ…
• VIVA: A Benchmark for Vision-Grounded Decision-Making with Human Values
  2024 · 具身智能 · Large vision language models (VLMs) have demonstrated significant potential for integration into daily life, making it crucial for them to incorporate human values when making decisions in real-world situations. This pap…
• LEGENT: Open Platform for Embodied Agents
  2024 · 具身智能 · Despite advancements in Large Language Models (LLMs) and Large Multimodal Models (LMMs), their integration into language-grounded, human-like embodied agents remains incomplete, hindering complex real-life task performan…
• Open-ended VQA benchmarking of Vision-Language models by exploiting Classification datasets and their semantic hierarchy
  2024 · 具身智能 · The evaluation of text-generative vision-language models is a challenging yet crucial endeavor. By addressing the limitations of existing Visual Question Answering (VQA) benchmarks and proposing innovative evaluation met…
• VLN-Video: Utilizing Driving Videos for Outdoor Vision-and-Language Navigation
  2024 · 具身智能 · Outdoor Vision-and-Language Navigation (VLN) requires an agent to navigate through realistic 3D outdoor environments based on natural language instructions. The performance of existing VLN methods is limited by insuffici…
• AstroMLab 1: Who Wins Astronomy Jeopardy!?
  2024 · 地外科学 · We present a comprehensive evaluation of proprietary and open-weights large language models using the first astronomy-specific benchmarking dataset. This dataset comprises 4,425 multiple-choice questions curated from the…
• Grading Massive Open Online Courses Using Large Language Models
  2024 · 地外科学 · Massive open online courses (MOOCs) offer free education globally. Despite this democratization of learning, the massive enrollment in these courses makes it impractical for an instructor to assess every student's writin…
• MLLM-LLaVA-FL: Multimodal Large Language Model Assisted Federated Learning
  2024 · 隐私计算与数据要素 · Previous studies on federated learning (FL) often encounter performance degradation due to data heterogeneity among different clients. In light of the recent advances in multimodal large language models (MLLMs), such as …
• Communication-Efficient Personalized Federated Learning for Speech-to-Text Tasks
  2024 · 隐私计算与数据要素 · To protect privacy and meet legal regulations, federated learning (FL) has gained significant attention for training speech-to-text (S2T) systems, including automatic speech recognition (ASR) and speech translation (ST).…
• Safely Learning with Private Data: A Federated Learning Framework for Large Language Model
  2024 · 隐私计算与数据要素 · Private data, being larger and quality-higher than public data, can greatly improve large language models (LLM). However, due to privacy concerns, this data is often dispersed in multiple silos, making its secure utiliza…
• Federated Large Language Models: Current Progress and Future Directions
  2024 · 隐私计算与数据要素 · Large Language Models have achieved impressive performance across diverse applications, yet their training typically depends on centralized data collection, raising serious privacy and governance concerns. Federated Lear…
• TCM-FTP: Fine-Tuning Large Language Models for Herbal Prescription Prediction
  2024 · 中医药工具 · Traditional Chinese medicine (TCM) has relied on specific combinations of herbs in prescriptions to treat various symptoms and signs for thousands of years. Predicting TCM prescriptions poses a fascinating technical chal…
• Human-centered NLP Fact-checking: Co-Designing with Fact-checkers using Matchmaking for AI
  2023 · AI 安全与对齐 · While many Natural Language Processing (NLP) techniques have been proposed for fact-checking, both academic research and fact-checking organizations report limited adoption of such NLP work due to poor alignment with fac…
• Split and Merge: Aligning Position Biases in LLM-based Evaluators
  2023 · AI 安全与对齐 · Large language models (LLMs) have shown promise as automated evaluators for assessing the quality of answers generated by AI systems. However, these LLM-based evaluators exhibit position bias, or inconsistency, when used…
• LMFlow: An Extensible Toolkit for Finetuning and Inference of Large Foundation Models
  2023 · AI 安全与对齐 · Foundation models have demonstrated a great ability to achieve general human-level intelligence far beyond traditional approaches. As the technique keeps attracting attention from the AI community, an increasing number o…
• SALMON: Self-Alignment with Instructable Reward Models
  2023 · AI 安全与对齐 · Supervised Fine-Tuning (SFT) on response demonstrations combined with Reinforcement Learning from Human Feedback (RLHF) constitutes a powerful paradigm for aligning LLM-based AI agents. However, a significant limitation …
• How Trustworthy are Open-Source LLMs? An Assessment under Malicious Demonstrations Shows their Vulnerabilities
  2023 · AI 安全与对齐 · The rapid progress in open-source Large Language Models (LLMs) is significantly driving AI development forward. However, there is still a limited understanding of their trustworthiness. Deploying these models at scale wi…
• Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Models
  2023 · AI 安全与对齐 · Language models have shown promise in various tasks but can be affected by undesired data during training, fine-tuning, or alignment. For example, if some unsafe conversations are wrongly annotated as safe ones, the mode…
• Preference Ranking Optimization for Human Alignment
  2023 · AI 安全与对齐 · Large language models (LLMs) often contain misleading content, emphasizing the need to align them with human values to ensure secure AI systems. Reinforcement learning from human feedback (RLHF) has been employed to achi…

以 API 获取该主题全量数据

# 主题词表（含本主题的站点分布与年度分布）
curl http://data.swarmlabs.tools/api/topics.json

# 主题共现知识图谱
curl http://data.swarmlabs.tools/api/graph.json

需要按主题批量拉取、导出 BibTeX 或接入 AI Agent？查看 数据下载与格式 或 MCP 接入。