Knowledge catalogue
arXiv:2604.19765v1 Announce Type: cross Abstract: Recent work identifies a sparse set of 'hallucination neurons' (H-neurons), less than 0.1% of feed-forward network neurons, that reliably predict when
arXiv:2604.20544v1 Announce Type: cross Abstract: The efficacy of Large Vision-Language Models (LVLMs) is critically dependent on the quality of their training data, requiring a precise balance betwee
arXiv:2604.20570v1 Announce Type: new Abstract: Spatial intelligence is essential for multimodal large language models, yet current benchmarks largely assess it only from an understanding perspective.
arXiv:2604.20288v1 Announce Type: new Abstract: Flight diversions are rare but high-impact events in aviation, making their reliable prediction vital for both safety and operational efficiency. Howeve
arXiv:2308.03303v2 Announce Type: replace Abstract: Fine-tuning large language models (LLMs) is crucial for improving their performance on downstream tasks, but full-parameter fine-tuning (Full-FT) is
arXiv:2604.20413v1 Announce Type: new Abstract: Large language models perform well on many reasoning tasks, yet they often lack awareness of whether their current knowledge or reasoning state is compl
arXiv:2511.19328v2 Announce Type: replace Abstract: Language modeling has shown us that transformers can discover latent structure from context, but the dynamics of how they acquire different componen
arXiv:2604.19858v1 Announce Type: new Abstract: We present Wan-Image, a unified visual generation system explicitly engineered to paradigm-shift image generation models from casual synthesizers into p
arXiv:2604.20350v1 Announce Type: new Abstract: Despite significant progress in Multi-modal Large Language Models (MLLMs), their clinical reasoning capacity for multi-modal diagnosis remains largely u
arXiv:2604.19281v1 Announce Type: cross Abstract: The use of Large Language Models (LLMs) to support patients in addressing medical questions is becoming increasingly prevalent. However, most of the m
arXiv:2604.18587v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated significant potential in formal theorem proving, yet state-of-the-art performance often necessitates pr
arXiv:2604.02923v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs), particularly those employing Mixture-of-Experts (MoE) architectures, have achieved remarkable capabilities acros
arXiv:2604.18963v1 Announce Type: cross Abstract: Knowledge distillation (KD) transfers capabilities from large language models (LLMs) to smaller students, yet it can fail unpredictably and also under
This article demonstrates running Gemma 4, Google's open-weight language model, on NVIDIA's Jetson Orin Nano Super edge computing device. It likely covers the model's capabilities, performance metrics
arXiv:2604.18887v1 Announce Type: new Abstract: Reduced-order models are powerful for analyzing and controlling high-dimensional dynamical systems. Yet constructing these models for complex hybrid sys
arXiv:2507.03828v4 Announce Type: replace Abstract: Large language models (LLMs) achieve strong performance across diverse domains but remain difficult to deploy in resource-constrained environments d
arXiv:2604.18759v1 Announce Type: new Abstract: Class imbalance is a widespread challenge in NLP tasks, significantly hindering robust performance across diverse domains and applications. We introduce
arXiv:2603.11665v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have been widely adopted as MLLM-as-a-Judges due to their strong alignment with human judgment across vario
arXiv:2512.19442v3 Announce Type: replace-cross Abstract: Diffusion-based generative models have greatly impacted the speech processing field in recent years, exhibiting high speech naturalness and sp
arXiv:2508.01959v2 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) over long documents typically involves splitting the text into smaller chunks, which serve as the basic units f
arXiv:2604.18756v1 Announce Type: cross Abstract: Large Language Models (LLMs) remain vulnerable to optimization-based jailbreak attacks that exploit internal gradient structure. While Sparse Autoenco
arXiv:2604.19221v1 Announce Type: new Abstract: Full-duplex speech interaction, as the most natural and intuitive mode of human communication, is driving artificial intelligence toward more human-like
arXiv:2604.19001v1 Announce Type: new Abstract: Large reasoning models (LRMs) produce complex, multi-step reasoning traces, yet safety evaluation remains focused on final outputs, overlooking how harm
arXiv:2604.18586v1 Announce Type: cross Abstract: Vaccination remains a cornerstone of global public health, yet the COVID-19 pandemic exposed how online misinformation, political polarization, and de
arXiv:2604.17183v1 Announce Type: cross Abstract: Bitcoin transaction fees will become more important as the block subsidy declines, but fee formation is hard to study with blockchain data alone becau
arXiv:2604.17073v1 Announce Type: new Abstract: Reinforcement fine-tuning improves the reasoning ability of large language models, but it can also encourage them to answer unanswerable queries by gues
arXiv:2604.16879v1 Announce Type: new Abstract: With the rapid development of generative models and multimodal content editing technologies, the key challenge faced by synthetic image detection (SID)
arXiv:2510.07143v3 Announce Type: replace Abstract: Recent efforts to accelerate inference in Multimodal Large Language Models (MLLMs) have largely focused on visual token compression. The effectivene
arXiv:2604.18169v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for creative tasks such as literary translation. Yet translational creativity remains underexplored a
arXiv:2604.17299v1 Announce Type: new Abstract: Aligning large language models with human preferences must balance two competing goals: responding helpfully to legitimate requests and reliably refusin
arXiv:2604.16400v1 Announce Type: cross Abstract: As Large Language Models (LLMs) are increasingly adopted in edge intelligence to power domain-specific applications and personalized services, the qua
arXiv:2604.16391v1 Announce Type: cross Abstract: Vision-language-action (VLA) models have shown great potential in building generalist robots, but still face a dilemma-misalignment of 2D image foreca
arXiv:2510.11288v4 Announce Type: replace Abstract: Recent work has shown that narrow finetuning can produce broadly misaligned LLMs, a phenomenon termed emergent misalignment (EM). While concerning,
arXiv:2604.18379v1 Announce Type: new Abstract: Most data-driven ionospheric forecasting models operate on gridded products, which do not preserve the time-varying sampling structure of satellite-base
arXiv:2604.18547v1 Announce Type: cross Abstract: Verification of model outputs is rapidly emerging as a key primitive for both training and real-world deployment of large language models (LLMs). In p
arXiv:2604.17751v1 Announce Type: cross Abstract: Adapting foundation models under resource budgets relies heavily on Parameter-Efficient Fine-Tuning (PEFT), with LoRA being a standard modular solutio
This appears to be a social media post from Ollama's X account regarding a model run command for 'kimi-k2.6:cloud,' likely announcing or demonstrating how to execute this specific AI model variant usi
arXiv:2604.18381v1 Announce Type: cross Abstract: Fine-tuning Large Language Models (LLMs) typically relies on large quantities of high-quality annotated data, or questions with well-defined ground tr
arXiv:2511.07129v3 Announce Type: replace Abstract: Low-Rank Adaptation (LoRA) has emerged as a parameter-efficient approach for fine-tuning large language models. However, conventional LoRA adapters
arXiv:2604.16506v1 Announce Type: cross Abstract: Large language models perform well on many medical QA benchmarks, but real clinical reasoning often requires integrating evidence across multiple imag
arXiv:2512.21510v2 Announce Type: replace-cross Abstract: Real-world multi-view data often exhibit highly inconsistent missing patterns, posing significant challenges for incomplete multi-view cluster
arXiv:2604.18311v1 Announce Type: new Abstract: Explainable AI (XAI) aims to make the behaviour of machine learning models interpretable, yet many explanation methods remain difficult to understand. T
arXiv:2604.17219v1 Announce Type: cross Abstract: We derive explicit non-asymptotic PAC-Bayes generalization bounds for Gibbs posteriors, that is, data-dependent distributions over model parameters ob
arXiv:2604.17570v1 Announce Type: new Abstract: Peripheral Blood Smear (PBS) is a critical microscopic examination in hematopathology that yields whole-slide imaging (WSI). Unlike solid tissue patholo
arXiv:2604.17831v1 Announce Type: new Abstract: Neural surface reconstruction methods typically treat camera poses as fixed values, assuming perfect accuracy from Structure-from-Motion (SfM) systems.
arXiv:2604.17800v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have gained much attention from the research community thanks to their strength in translating multimodal observat
arXiv:2604.17175v1 Announce Type: new Abstract: We introduce RosettaSearch, an inference-time multi-objective optimization approach for protein sequence optimization. We use large language models (LLM
arXiv:2604.16362v1 Announce Type: cross Abstract: Data scarcity and weak supervision continue to limit the performance of machine learning models in many real-world applications, such as mammography,
arXiv:2604.17739v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a prevalent paradigm for training tool calling agents, which typically requires online interactive environments
arXiv:2604.18264v1 Announce Type: new Abstract: Zeroth-Order optimization presents a promising memory-efficient paradigm for fine-tuning Large Language Models by relying solely on forward passes. Howe
arXiv:2604.16259v1 Announce Type: cross Abstract: Frontier models have demonstrated exceptional capabilities following the integration of task-reward-based reinforcement learning (RL) into their train
arXiv:2510.24328v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly used to answer everyday questions, yet their performance on culturally grounded and dialectal co
arXiv:2604.15503v1 Announce Type: new Abstract: Recent breakthroughs in language models (LMs) using neural networks have raised the question: how similar are these models' processing to human language
arXiv:2604.15521v1 Announce Type: new Abstract: Flow matching models have emerged as a powerful framework for realistic image generation by learning to reverse a corruption process that progressively
arXiv:2604.15671v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have demonstrated significant potential for embodied decision-making; however, their application in complex chemical
arXiv:2604.16146v1 Announce Type: new Abstract: Recent works proposed test-time alignment methods that rely on a small aligned model as a proxy that guides the generation of a larger base (unaligned)
arXiv:2604.15494v1 Announce Type: cross Abstract: Deep networks that rely on prototypes-interpretable representations that can be related to the model input-have gained significant attention for balan
arXiv:2604.15736v1 Announce Type: cross Abstract: While Multimodal Large Language Models (MLLMs) excel at generic video understanding, their ability to support specialized, rule-grounded decision-maki
arXiv:2510.27617v2 Announce Type: replace Abstract: Automation of Register Transfer Level (RTL) design can help developers meet increasing computational demands. Large Language Models (LLMs) show prom
arXiv:2604.14191v1 Announce Type: new Abstract: State Space Models (SSMs) such as Mamba have become a popular alternative to Transformer models, due to their reduced memory consumption and higher thro