Papers General Knowledge
“General Knowledge” 태그가 달린 논문 552편 · 필터 해제
Industrial-Instruction: An End-to-End Framework for Building Instruction-Tuning and Benchmark Datasets from Industrial Technical Reports
Industrial technical reports contain high-value knowledge for maintenance, troubleshooting, and product engineering, but their heterogeneous structure (dense prose, specifications, tables) makes them difficult to index a…
Semantic RetrievalGeneral KnowledgetinyDSM: A Framework for Skill Modeling and Development for Resource-Constrained Millirobots
In this study, we investigate developmental mechanisms that enable small, resource-constrained systems such as cm-sized millirobots to autonomously explore, learn, and adapt their capabilities throughout their lifespan. …
Reinforcement LearningGeneral KnowledgeGrid-Preserving Knowledge Distillation: Transferring Convolutional Inductive Bias to Vision Transformers under Data Scarcity
Vision Transformers demonstrate remarkable global modeling capacity but often underperform in data-scarce regimes. Distilling convolutional inductive biases from a CNN teacher provides an effective remedy while leaving t…
Knowledge DistillationGeneral KnowledgeAn AI4AI Framework for Visual Token Pruning
Visual-token pruning can substantially reduce the inference cost of multimodal large language models (MLLMs), yet existing methods largely rely on fixed, handcrafted heuristics and costly expert trial and error. As pruni…
General KnowledgeFairness Pruning: Locating Demographic Bias in GLU-MLP Layers via Differential Activations
This work presents Fairness Pruning, a lightweight structural intervention method designed for the management and future mitigation of demographic bias in large language models (LLMs). As a foundational empirical validat…
General KnowledgeText GenerationUNIT: Unleash Large Language Models Potential for Graph Continual Learning
In real-world multimodal web scenarios, graph-structured data often arrives in a streaming manner, making graph continual learning a crucial paradigm for continuously modeling such evolving structures. However, existing …
Continual LearningGeneral KnowledgeDKCD: Domain Knowledge-Enhanced Causal Discovery from Unstructured Data
Causal discovery from unstructured data is a challenging yet underexplored task in high-expertise domains such as healthcare, finance, and education. Existing methods typically leverage the general knowledge of large lan…
General KnowledgeWill Scaling Improve Social Simulation with LLMs?
Large Language Model (LLM) social simulations are a promising research method, but they are not yet faithful enough to be adopted widely. In this work, we investigate whether the current scaling paradigm in language mode…
General KnowledgePre-Flight: A Benchmark for Evaluating Large Language Models on Aviation Operational Knowledge
Large language models (LLMs) are increasingly proposed for aviation business operations, from documentation and training generation to customer facing assistants. General purpose benchmarks do not measure whether a model…
General KnowledgeAGC-Bench: Measuring Artificial General Creativity
Creativity research has debated whether creativity is domain-specific (e.g., visual, writing, science), and if it is psychometrically separable from general intelligence. Both questions now apply to LLMs, but a unified b…
General KnowledgeFew-Shot Domain Incremental Learning via Continual Vision-Language Consolidation
Existing domain-incremental learning (DIL) strategies call for massive amounts of data to adapt to new domains and suffer from the overfitting problem in the case of data scarcity. This paper puts forward a relatively un…
parameter-efficient fine-tuningIncremental LearningGeneral KnowledgePreventing Error Propagation in Multi-Agent AI through Runtime Monitoring
Multi-agent AI systems can improve answer selection by allowing different language models to exchange reasoning traces, revise initial predictions, and support a final decision. However, such communication may also intro…
General KnowledgeAnswer SelectionNebulaExp-8B: An Empirical Post-Training Pipeline via Full-Scale Ablation Research
Post-training alignment determines the reasoning and human preference following capabilities of large language models, yet most existing works withhold detailed data construction, filtering rules and training recipes, wh…
Reinforcement LearningMathematical ReasoningGeneral KnowledgeCode GenerationCurvature-Guided Mixing for MLLM Adaptation
Fine-tuning Multimodal Large Language Models (MLLMs) on specialized tasks often leads to catastrophic forgetting of their general capabilities. Existing model merging methods to combat this are often heuristic or use sub…
General KnowledgeScaling Laws for Task-Specific LLM Distillation
Large Language Models (LLMs) achieve strong performance across a growing range of domains, yet their scale poses deployment challenges in applications where latency and cost constraints are critical. This paper derives e…
General KnowledgeLESS Is More: Mutual-Stability Sampling for Diffusion Language Models
Diffusion large language models (dLLMs) offer a promising alternative to autoregressive decoding by iteratively refining masked sequences, enabling parallel token updates and bidirectional conditioning. Their practical e…
General KnowledgeAuthority, Truth, and Citation Bias: A Large-Scale Multi-Domain Benchmark for Studying Epistemic Susceptibility in Large Language Models
Large language models are increasingly deployed in citation-augmented settings, yet the effect of citation presence on model behavior independent of factual content remains poorly understood. We introduce AuthorityBench,…
General KnowledgeSelf-Recognition Finetuning can Prevent and Reverse Emergent Misalignment
Emergent misalignment (EM) has been linked to the activation of misaligned persona vectors and evil character traits, suggesting that EM operates through disruption of the model's aligned character rather than direct lea…
General KnowledgeAnnotations Are Not All You Need: A Cross-modal Knowledge Transfer Network for Unsupervised Temporal Sentence Grounding
This paper addresses the task of temporal sentence grounding (TSG). Although many respectable works have made decent achievements in this important topic, they severely rely on massive expensive video-query paired annota…
Temporal Sentence GroundingGeneral KnowledgeParameter Alignment Mitigates Catastrophic Forgetting in Multilingual Expert Language Models
While continual pretraining~(CPT) is a practical way to extend large language models to new languages, naïve finetuning on targeted data erodes existing capabilities through catastrophic forgetting. Organizing training a…
Reading ComprehensionContinual PretrainingLanguage AcquisitionGeneral Knowledge