Latest AI/ML News
2784 articles · arXiv cs.CL
arXiv:2609.18009v2 Announce Type: replace-cross Abstract: Lightweight audio-visual speech enhancement (AVSE) models face a critical trade-off between…
arXiv:2609.19113v2 Announce Type: replace Abstract: We evaluate six frontier language models on the two-agent $\log_2 N$-Questions game (Potash et al.…
arXiv:2609.15991v2 Announce Type: replace Abstract: Standard subword tokenizers either treat every orthographic variation of a word (such as hello, He…
arXiv:2608.27409v2 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) improves specific capabilities of large lang…
arXiv:2608.15641v2 Announce Type: replace Abstract: This paper evaluates Wiktionary as an ethically crowdsourced lexicon for English dialects. We took…
arXiv:2608.11742v2 Announce Type: replace Abstract: Diffusion Large Language Models (dLLMs) have emerged as a competitive alternative to autoregressiv…
arXiv:2606.24595v2 Announce Type: replace Abstract: Long-term memory promises LLM agents that grow more capable across sessions, maintaining an accura…
arXiv:2605.29343v3 Announce Type: replace Abstract: Speculative decoding accelerates large language model inference by pairing a target model with a l…
arXiv:2605.17710v2 Announce Type: replace Abstract: Although modern multilingual Automatic Speech Recognition (ASR) systems support several Nigerian l…
arXiv:2604.23478v3 Announce Type: replace Abstract: Large language models are widely used to judge the output of other language models, yet whether a…
arXiv:2602.16313v2 Announce Type: replace Abstract: Existing evaluations of agents with memory typically assess memorization and action in isolation.…
arXiv:2601.06848v2 Announce Type: replace Abstract: Multimodal aspect-based sentiment analysis (MABSA) aims to identify aspect-level sentiments by joi…
arXiv:2511.13254v2 Announce Type: replace Abstract: Large Language Models (LLMs) have displayed remarkable capabilities across diverse domains, but th…
arXiv:2505.10202v2 Announce Type: replace Abstract: Large Language Models (LLMs) have achieved remarkable success but face significant computational a…
arXiv:2503.16094v2 Announce Type: replace Abstract: Large Language Model (LLM) alignment is commonly achieved through supervised fine-tuning or reinfo…
arXiv:2309.13476v3 Announce Type: replace Abstract: Depression is a common mental disorder. Automatic depression detection tools using speech, enabled…
arXiv:2609.21793v1 Announce Type: cross Abstract: Defenses against jailbreak attacks on Large Language Models (LLMs) operate at different pipeline sta…
arXiv:2609.21676v1 Announce Type: cross Abstract: We present the Spoken Wikipedia Presentation Corpus, an extension of the Spoken Wikipedia Corpora fe…
arXiv:2609.21340v1 Announce Type: cross Abstract: Empirical identity leakage from released text is increasingly driven by attackers that combine large…
arXiv:2609.21183v1 Announce Type: cross Abstract: Audio large language models (AudioLLMs) operate reactively, responding only when queried. We introdu…