Stay updated with the latest research and technology news
arXiv:2601.18777v1 Announce Type: new Abstract: Evaluating the quality of search, ranking and RAG systems traditionally requires a significant number of human relevance annotations. In recent...
arXiv:2601.18778v1 Announce Type: new Abstract: Can a model learn to escape its own learning plateau? Reinforcement learning methods for finetuning large reasoning models stall on...
arXiv:2601.18779v1 Announce Type: new Abstract: Reinforcement learning (RL) has improved the reasoning abilities of large language models (LLMs), yet state-of-the-art methods still fail to learn...
arXiv:2601.18783v1 Announce Type: new Abstract: Balancing safety, efficiency, and operational costs in highway driving poses a challenging decision-making problem for heavy-duty vehicles. A central difficulty...
arXiv:2601.18785v1 Announce Type: new Abstract: The rise of Large Language Models (LLMs) has enabled a new paradigm for bridging authorial intent and player agency in...
arXiv:2601.18788v1 Announce Type: new Abstract: Unsupervised text segmentation is crucial because boundary labels are expensive, subjective, and often fail to transfer across domains and granularity...
arXiv:2601.18790v1 Announce Type: new Abstract: Large Language Models are increasingly optimized for deep reasoning, prioritizing the correct execution of complex tasks over general conversation. We...
arXiv:2601.18791v1 Announce Type: new Abstract: We present a large-scale comparative study of 242 Latin and Cyrillic-script languages using subword-based methodologies. By constructing 'glottosets' from Wikipedia...
arXiv:2601.18792v1 Announce Type: new Abstract: Decoding emotion from brain activity could unlock a deeper understanding of the human experience. While a number of existing datasets...
arXiv:2601.18793v1 Announce Type: new Abstract: Metaprogramming and effect handlers interact in unexpected, and sometimes undesirable, ways. One example is scope extrusion: the generation of ill-scoped...
arXiv:2601.18795v1 Announce Type: new Abstract: Typical reinforcement learning (RL) methods for LLM reasoning waste compute on hard problems, where correct on-policy traces are rare, policy...
arXiv:2601.18796v1 Announce Type: new Abstract: Text embeddings have become an essential part of a variety of language applications. However, methods for interpreting, exploring and reversing...
arXiv:2505.03210v3 Announce Type: cross Abstract: In this paper, we survey physically related applications of a class of weighted quasi-Monte Carlo methods from a theoretical, deterministic...
arXiv:2601.15801v1 Announce Type: cross Abstract: While Large Language Models (LLMs) are aligned to mitigate risks, their safety guardrails remain fragile against jailbreak attacks. This reveals...
arXiv:2601.16989v1 Announce Type: cross Abstract: Speech-based detection of cognitive impairment offers a scalable, non-invasive screening, yet algorithmic bias across demographic and linguistic subgroups remains critically...
arXiv:2601.17014v1 Announce Type: cross Abstract: BickGraphing is a browser based research tool that enables visual inspection of acoustic recordings. The tool was built in support...
arXiv:2601.17021v1 Announce Type: cross Abstract: We attempt to mitigate the persistent tradeoff between risk and return in medium- to long-term portfolio management. This paper proposes...
arXiv:2601.17061v1 Announce Type: cross Abstract: Information can evolve as a physical consequence of non-equilibrium dynamics, even in the absence of genes, replication, or predefined fitness...
arXiv:2601.17080v1 Announce Type: cross Abstract: Automated respiratory sound classification supports the diagnosis of pulmonary diseases. However, many deep models still rely on cycle-level analysis and...
arXiv:2601.17084v1 Announce Type: cross Abstract: The discovery of high-performance organic photocatalysts for hydrogen evolution remains limited by the vastness of chemical space and the reliance...
arXiv:2601.17085v1 Announce Type: cross Abstract: Discrete speech tokens offer significant advantages for storage and language model integration, but their application in speech emotion recognition (SER)...
arXiv:2601.17126v1 Announce Type: cross Abstract: While deep learning is transforming data analysis in high-energy physics, computational challenges limit its potential. We address these challenges in...
arXiv:2601.17142v1 Announce Type: cross Abstract: In this work we study quantitative existence results for genus-$2$ curves over $\mathbb{Q}$ whose Jacobians have Mordell-Weil rank at least...
arXiv:2601.17146v1 Announce Type: cross Abstract: Empirical investigations into unintended model behavior often show that the algorithm is predicting another outcome than what was intended. These...