Learning When to Trust via Selective Context Preference Optimization
Frames robustness as selective trust and trains language models to resist misleading signals without ignoring useful context.
reliabilitypreference optimizationevaluation
Artificial Intelligence
Foundation models, reasoning, agents, evaluation, reliability, and model architectures.
31 curated papers31 papers
2026
2 papersAgentic Artificial Intelligence: Architectures, Taxonomies, and Evaluation of Large Language Model Agents
Proposes a unified taxonomy for agent perception, planning, action, tool use, collaboration, environments, and evaluation.
agentstaxonomyevaluation
2025
12 papersIndustry researchAmazon (United States)62 citations
A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness
Large language models (LLMs) have demonstrated emergent abilities in text generation, question answering, and reasoning, facilitating various tasks and domains. Despite their proficiency in various tasks, LLMs like PaLM 540B and Llama-3.
Artificial IntelligenceLLM
Industry researchMicrosoft Research (United Kingdom)55 citations
Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey
Large language models (LLMs) have significantly advanced the field of natural language processing (NLP), providing a highly useful, task-agnostic foundation for a wide range of applications. However, directly applying LLMs to solve sophisticated problems in specific domains meets many hurdles, caused by the heterogeneity of domain data, the…
Artificial Intelligence
Industry researchHuawei Technologies (China)90 citations
A Survey on the Memory Mechanism of Large Language Model-based Agents
Large language model (LLM)-based agents have recently attracted much attention from the research and industry communities. Compared with original LLMs, LLM-based agents are featured in their self-evolving capability, which is the basis for solving real-world problems that need long-term and complex agent-environment interactions.
Artificial Intelligenceagents
Industry researchAmazon (United States) · Amazon (Germany) · Microsoft (United States) · Microsoft Research (United Kingdom)27 citations
Survey on Factuality in Large Language Models
This survey addresses the crucial issue of factuality in Large Language Models (LLMs). As LLMs find applications across diverse domains, the reliability and accuracy of their outputs become vital.
Artificial Intelligence
Industry researchAlibaba Group (Cayman Islands)40 citations
Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference
In recent years, applying multi-modal large language models (MLLMs) in various fields has achieved remarkable success. However, as the foundation model for many downstream tasks, MLLMs comprise the well-known Transformer network, which has a less efficient quadratic computation complexity.
Artificial Intelligence
Large Language Model Agent: A Survey on Methodology, Applications and Challenges
Organizes LLM-agent architecture, collaboration, evolution, evaluation, applications, and open research challenges.
agentssurveymulti-agent systems
Industry researchHuawei Technologies (China) · Huawei Technologies (Sweden)37 citations
NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning
Vision-and-Language Navigation (VLN), as a crucial research problem of Embodied AI, requires an embodied agent to navigate through complex 3D environments following natural language instructions. Recent research has highlighted the promising capacity of large language models (LLMs) in VLN by improving navigational reasoning accuracy and interpretability.
Artificial IntelligenceLLMreasoning
Industry researchHuawei Technologies (China)27 citations
An Empirical Study of Retrieval-Augmented Code Generation: Challenges and Opportunities
Code generation aims to automatically generate code snippets of specific programming language according to natural language descriptions. The continuous advancements in deep learning, particularly pre-trained models, have empowered the code generation task to achieve remarkable performance.
Artificial Intelligenceretrieval
Industry researchAlibaba Group (China)43 citations
Uni-MoE: Scaling Unified Multimodal LLMs With Mixture of Experts
Recent advancements in Multimodal Large Language Models (MLLMs) underscore the significance of scalable models and data to boost performance, yet this often incurs substantial computational costs. Although the Mixture of Experts (MoE) architecture has been employed to scale large language or visual-language models efficiently, these efforts typically…
Artificial IntelligenceLLMmultimodal
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Studies large-scale reinforcement learning for emergent reasoning and presents a multi-stage path to capable, readable reasoning models.
reasoningreinforcement learningLLM
Industry researchTencent (China)38 citations
AutoHMA-LLM: Efficient Task Coordination and Execution in Heterogeneous Multi-Agent Systems Using Hybrid Large Language Models
Heterogeneous multi-agent systems (HMAS) comprise various intelligent agents with specialized functions, such as drones, ground robots, and automated devices, working in coordinated settings. This paper presents AutoHMA-LLM, a novel framework that combines Large Language Models (LLMs) with classical control algorithms to address the challenges of task…
Artificial IntelligenceLLMagents
Industry researchMicrosoft (United States)103 citations
Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers
We introduce a language modeling approach for text to speech synthesis (TTS). Specifically, we train aneural codec language model(calledVALL-E) using discrete codes derived from an off-the-shelf neural audio codec model, and regard TTS as a conditional language modeling task rather than continuous signal regression as in previous work.
Artificial Intelligence
2024
17 papersTitans: Learning to Memorize at Test Time
Adds a neural long-term memory module that learns at inference time and complements attention's short-term context.
memoryarchitecturelong context
DeepSeek-V3 Technical Report
Describes a 671B-parameter mixture-of-experts model using latent attention, auxiliary-loss-free load balancing, and multi-token prediction.
mixture of expertsLLMtraining systems
Industry researchTencent (China)634 citations
A survey on multimodal large language models
Recently, the multimodal large language model (MLLM) represented by GPT-4V has been a new rising research hotspot, which uses powerful large language models (LLMs) as a brain to perform multimodal tasks. The surprising emergent capabilities of the MLLM, such as writing stories based on images and optical character recognition-free math reasoning, are…
Artificial Intelligencemultimodal
Industry researchTencent (China)248 citations
Large language models for generative information extraction: a survey
Abstract Information Extraction (IE) aims to extract structural knowledge from plain natural language texts. Recently, generative Large Language Models (LLMs) have demonstrated remarkable capabilities in text understanding and generation.
Artificial Intelligence
Industry researchTencent (China)47 citations
On the Effectiveness of Large Language Models in Domain-Specific Code Generation
Large language models (LLMs) such as ChatGPT have shown remarkable capabilities in code generation. Despite significant achievements, they rely on enormous training data to acquire a broad spectrum of open-domain knowledge.
Artificial Intelligence
Industry researchBaidu (China)649 citations
A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models
As one of the most advanced techniques in AI, Retrieval-Augmented Generation (RAG) can offer reliable and up-to-date external knowledge, providing huge convenience for numerous tasks. Particularly in the era of AI-Generated Content (AIGC), the powerful capacity of retrieval in providing additional knowledge enables RAG to assist existing generative AI…
Artificial IntelligenceLLMretrieval
Industry researchMicrosoft Research (United Kingdom)192 citations
Splitwise: Efficient Generative LLM Inference Using Phase Splitting
Generative large language model (LLM) applications are growing rapidly, leading to large-scale deployments of expensive and power-hungry GPUs. Our characterization of LLM inference shows that each inference request undergoes two phases: a compute-intensive prompt computation phase and a memory intensive token generation phase, each with distinct…
Artificial IntelligenceLLM
Industry researchBaidu (China)177 citations
Exploring the Potential of Large Language Models (LLMs)in Learning on Graphs
Learning on Graphs has attracted immense attention due to its wide real-world applications. The most popular pipeline for learning on graphs with textual node attributes primarily relies on Graph Neural Networks (GNNs), and utilizes shallow text embedding as initial node representations, which has limitations in general knowledge and profound semantic…
Artificial IntelligenceLLM
Industry researchAmazon (United States)36 citations
CLIPSyntel: CLIP and LLM Synergy for Multimodal Question Summarization in Healthcare
In the era of modern healthcare, swiftly generating medical question summaries is crucial for informed and timely patient care. Despite the increasing complexity and volume of medical data, existing studies have focused solely on text-based summarization, neglecting the integration of visual information.
Artificial IntelligenceLLMmultimodal
Industry researchGoogle (United States) · Nvidia (United Kingdom)39 citations
Directed Diffusion: Direct Control of Object Placement through Attention Guidance
Text-guided diffusion models such as DALLE-2, Imagen, and Stable Diffusion are able to generate an effectively endless variety of images given only a short text prompt describing the desired image content. In many cases the images are of very high quality.
Artificial Intelligencediffusion
Industry researchAlibaba Group (United States)65 citations
FontDiffuser: One-Shot Font Generation via Denoising Diffusion with Multi-Scale Content Aggregation and Style Contrastive Learning
Automatic font generation is an imitation task, which aims to create a font library that mimics the style of reference images while preserving the content from source images. Although existing font generation methods have achieved satisfactory performance, they still struggle with complex characters and large style variations.
Artificial Intelligencediffusion
Industry researchTencent (China)763 citations
T2I-Adapter: Learning Adapters to Dig Out More Controllable Ability for Text-to-Image Diffusion Models
The incredible generative ability of large-scale text-to-image (T2I) models has demonstrated strong power of learning complex structures and meaningful semantics. However, relying solely on text prompts cannot fully take advantage of the knowledge learned by the model, especially when flexible and accurate controlling (e.
Artificial Intelligencediffusion
Industry researchAlibaba Group (China)63 citations
CodeKGC: Code Language Model for Generative Knowledge Graph Construction
Current generative knowledge graph construction approaches usually fail to capture structural knowledge by simply flattening natural language into serialized texts or a specification language. However, large generative language model trained on structured data such as code has demonstrated impressive capability in understanding natural language for…
Artificial Intelligenceedge
Industry researchMicrosoft Research Asia (China)2604 citations
A Survey on Evaluation of Large Language Models
Large language models (LLMs) are gaining increasing popularity in both academia and industry, owing to their unprecedented performance in various applications. As LLMs continue to play a vital role in both research and daily use, their evaluation becomes increasingly critical, not only at the task level, but also at the society level for better…
Artificial Intelligence
Industry researchTencent (China)286 citations
A Survey on Multimodal Large Language Models for Autonomous Driving
With the emergence of Large Language Models (LLMs) and Vision Foundation Models (VFMs), multimodal AI systems benefiting from large models have the potential to equally perceive the real world, make decisions, and control tools as humans. In recent months, LLMs have shown widespread attention in autonomous driving and map systems.
Artificial Intelligencemultimodal
Industry researchAdobe Systems (United States) · Intel (United States)570 citations
Bias and Fairness in Large Language Models: A Survey
Abstract Rapid advancements of large language models (LLMs) have enabled the processing, understanding, and generation of human-like text, with increasing integration into systems that touch our social sphere. Despite this success, these models can learn, perpetuate, and amplify harmful social biases.
Artificial Intelligence
Industry researchAlibaba Group (United States)244 citations
Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation
Large language models (LLMs) have emerged as a new paradigm for Text-to-SQL task. However, the absence of a systematical benchmark inhibits the development of designing effective, efficient and economic LLM-based Text-to-SQL solutions.
Artificial Intelligence
No matching papers.Try a broader title, author, topic, or year.