Stay updated with the latest research and technology news
arXiv:2602.17542v1 Announce Type: new Abstract: Fine-grained skill representations, commonly referred to as knowledge components (KCs), are fundamental to many approaches in student modeling and learning...
arXiv:2602.17544v1 Announce Type: new Abstract: In multi-agent IR pipelines for tasks such as search and ranking, LLM-based agents exchange intermediate reasoning in terms of Chain-of-Thought...
arXiv:2602.17546v1 Announce Type: new Abstract: Instruction-following language models are trained to be helpful and safe, yet their safety behavior can deteriorate under benign fine-tuning and...
arXiv:2602.17547v1 Announce Type: new Abstract: This paper introduces KLong, an open-source LLM agent trained to solve extremely long-horizon tasks. The principle is to first cold-start...
arXiv:2602.17550v1 Announce Type: new Abstract: Existing Reinforcement Learning with Verifiable Rewards (RLVR) algorithms, such as GRPO, rely on rigid, uniform, and symmetric trust region mechanisms...
arXiv:2602.17552v1 Announce Type: new Abstract: Error-bounded lossy compression is essential for managing the massive data volumes produced by large-scale HPC simulations. While state-of-the-art compressors such...
arXiv:2602.17554v1 Announce Type: new Abstract: Training large-scale generative models is resource-intensive and relies heavily on heuristic dataset weighting. We address two fundamental questions: Can we...
arXiv:2602.17555v1 Announce Type: new Abstract: Video reasoning requires understanding the causal relationships between events in a video. However, such relationships are often implicit and costly...
arXiv:2602.17558v1 Announce Type: new Abstract: Recent advances in multimodal large language models (MLLMs) have shown great potential for extending vision-language reasoning to professional tool-based image...
arXiv:2602.17559v1 Announce Type: new Abstract: Continual Learning (CL) with large-scale pre-trained models (PTMs) has recently gained wide attention, shifting the focus from training from scratch...
arXiv:2602.17560v1 Announce Type: new Abstract: Activation steering, or representation engineering, offers a lightweight approach to align large language models (LLMs) by manipulating their internal activations...
arXiv:2602.17566v1 Announce Type: new Abstract: The significant advancements in computational power cre- ate a vast opportunity for using Artificial Intelligence in different ap- plications of...
arXiv:2602.17568v1 Announce Type: new Abstract: Normalization and scaling are fundamental preprocessing steps in time series modeling, yet their role in Transformer-based models remains underexplored from...
arXiv:2602.17573v1 Announce Type: new Abstract: The ever increasing intensity and number of disasters make even more difficult the work of First Responders (FRs). Artificial intelligence...
arXiv:2602.17574v1 Announce Type: new Abstract: Embedded optimization-based planning for hybrid systems is challenging due to the use of mixed-integer programming, which is computationally intensive and...
arXiv:2602.17577v1 Announce Type: new Abstract: Omniprediction is a learning problem that requires suboptimality bounds for each of a family of losses $\mathcal{L}$ against a family...
arXiv:2602.17584v1 Announce Type: new Abstract: As models and data scale, independently trained networks often induce analogous notions of similarity. But, matching similarities is weaker than...
arXiv:2602.17586v1 Announce Type: new Abstract: Safety validation for Level 4 autonomous vehicles (AVs) is currently bottlenecked by the inability to scale the detection of rare,...
arXiv:2602.17588v1 Announce Type: new Abstract: Despite rapid progress in autonomous web agents, human involvement remains essential for shaping preferences and correcting agent behavior as tasks...
arXiv:2602.17590v1 Announce Type: new Abstract: We present BMC4TimeSec, an end-to-end tool for verifying Timed Security Protocols (TSP) based on SMT-based bounded model checking and multi-agent...
arXiv:2602.17594v1 Announce Type: new Abstract: Rigorously evaluating machine intelligence against the broad spectrum of human general intelligence has become increasingly important and challenging in this...
arXiv:2602.17596v1 Announce Type: new Abstract: We study the topology of the loss landscape of one-hidden-layer ReLU networks under overparameterization. On the theory side, we (i)...
arXiv:2602.17598v1 Announce Type: new Abstract: Current speech LLMs largely perform implicit ASR: on tasks solvable from a transcript, they are behaviorally and mechanistically equivalent to...
arXiv:2602.17599v1 Announce Type: new Abstract: Music generation has advanced markedly through multimodal deep learning, enabling models to synthesize audio from text and, more recently, from...