Stay updated with the latest research and technology news
arXiv:2602.01728v1 Announce Type: new Abstract: Decoding the human brain from electroencephalography (EEG) signals holds promise for understanding neurological activities. However, EEG data exhibit heterogeneity across...
arXiv:2602.01729v1 Announce Type: new Abstract: This study explores a streamlined facial data collection method for conversational contexts, addressing the limitations of existing approaches that often...
arXiv:2602.01731v1 Announce Type: new Abstract: Non-prehensile manipulation using onboard sensing presents a fundamental challenge: the manipulated object occludes the sensor's field of view, creating occluded...
arXiv:2602.01734v1 Announce Type: new Abstract: Training instability remains a critical challenge in large language model (LLM) pretraining, often manifesting as sudden gradient explosions that waste...
arXiv:2602.01736v1 Announce Type: new Abstract: Recent work has questioned the effectiveness and robustness of neural network architectures for time series forecasting tasks. We summarize these...
arXiv:2602.01738v1 Announce Type: new Abstract: While specialized detectors for AI-Generated Images (AIGI) achieve near-perfect accuracy on curated benchmarks, they suffer from a dramatic performance collapse...
arXiv:2602.01740v1 Announce Type: new Abstract: Video language models (Video-LLMs) are prone to hallucinations, often generating plausible but ungrounded content when visual evidence is weak, ambiguous,...
arXiv:2602.01741v1 Announce Type: new Abstract: The burgeoning complexity and scale of 3D geometry models pose significant challenges for deployment on resource-constrained platforms. While Post-Training Quantization...
arXiv:2602.01744v1 Announce Type: new Abstract: While linear attention reduces the quadratic complexity of standard Transformers to linear time, it often lags behind in expressivity due...
arXiv:2602.01745v1 Announce Type: new Abstract: Token-level reweighting is a simple yet effective mechanism for controlling supervised fine-tuning, but common indicators are largely one-dimensional: the ground-truth...
arXiv:2602.01746v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) is widely used for federated fine-tuning. Yet under non-IID settings, it can substantially underperform full-parameter fine-tuning. Through...
arXiv:2602.01747v1 Announce Type: new Abstract: Automated Essay Scoring (AES) plays a crucial role in education by providing scalable and efficient assessment tools. However, in real-world...
arXiv:2602.01748v1 Announce Type: new Abstract: We propose OFERA, a novel framework for real-time expression control of photorealistic Gaussian head avatars for VR headset users. Existing...
arXiv:2602.01749v1 Announce Type: new Abstract: Generative Flow Network (GFlowNet) objectives implicitly fix an equal mixing of forward and backward policies, potentially constraining the exploration-exploitation trade-off...
arXiv:2602.01750v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) remains vulnerable to reward hacking, where models exploit spurious correlations in learned reward models...
arXiv:2602.01751v1 Announce Type: new Abstract: Predicting drug-drug interactions (DDIs) is essential for safe pharmacological treatments. Previous graph neural network (GNN) models leverage molecular structures and...
arXiv:2602.01752v1 Announce Type: new Abstract: As large language models (LLMs) generate increasingly human-like text, watermarking offers a promising solution for reliable attribution beyond mere detection....
arXiv:2602.01753v1 Announce Type: new Abstract: Aligning objects with corresponding textual descriptions is a fundamental challenge and a realistic requirement in vision-language understanding. While recent multimodal...
arXiv:2602.01754v1 Announce Type: new Abstract: Smart parking systems help reduce congestion and minimize users' search time, thereby contributing to smart city adoption and enhancing urban...
arXiv:2602.01755v1 Announce Type: new Abstract: An unweighted, undirected graph $G$ on $n$ nodes is said to have \emph{bandwidth} at most $k$ if its nodes can...
arXiv:2602.01756v1 Announce Type: new Abstract: While text-to-image generation has achieved unprecedented fidelity, the vast majority of existing models function fundamentally as static text-to-pixel decoders. Consequently,...
arXiv:2602.01757v1 Announce Type: new Abstract: The proliferation of retrieval-augmented generation (RAG) has established vector databases as critical infrastructure, yet they introduce severe privacy risks via...
arXiv:2602.01760v1 Announce Type: new Abstract: This paper focuses on a highly practical scenario: how to continue benefiting from the advantages of multi-modal image fusion under...
arXiv:2602.01762v1 Announce Type: new Abstract: Large Language Models (LLMs), constrained by their auto-regressive nature, suffer from slow decoding. Speculative decoding methods have emerged as a...