Category
20,463 papers
It is found that polarity blindness affects most evaluated models, and the effect persists across typologically differing negation systems, suggesting that polarity blindness reflects a broader limitation in semantic robustness rather than a language- or grammar-specific failure.
Large Language Models (LLMs) are increasingly used as research collaborators for hypothesis refinement, methodological planning, and technical analysis across multi-turn interactions. In this setting, a useful assistant must be accurate, methodologically justified, logically consistent, and token-efficient. Current ali...
Direct preference optimisation (DPO) is widely used for language model post-training, but its performance depends strongly on the choice of its hyperparameters, such as the learning rate and the reference-policy regularisation parameter $\beta$. To better understand the DPO hyperparameter landscape, we conduct extensiv...
Class-wise analyses, together with attention and masking analyses, show improved discrimination of ambiguous states and indicate that physical variables meaningfully constrain local response interpretation, and demonstrate a deployment-oriented approach to robust diagnosis in heterogeneous industrial environments.
Reach audiences
Advertise in front of researchers, engineers, and readers.
Code translation converts source code from one programming language to another while preserving its functionality. Although Large Language Models (LLMs) have improved code translation, their outputs still contain hallucinations: generated code that conflicts with the source program, violates target-language facts, or i...
Prompt-based contextual ASR requires selecting a compact hotword subset from large dynamic inventories, yet existing pre-selection methods rely either on discrete ASR hypotheses that may discard acoustic evidence or on separately trained retrieval models. We propose Viterbi-guided Selection of Hotwords (VISH), a traini...
Word error rate (WER) assigns equal cost to lexical edits despite their different semantic consequences, while overall semantic scores cannot identify which individual errors alter the intended meaning. We formulate ASR semantic evaluation as context-aware, segment-level consequence assessment and propose Semantic Segm...
The findings indicate that the retrieval balance of relevance and diversity substantially enhances the relevance and coverage of retrieved context in comparison to a conventional similarity search, with MMR raising nDCG@5 by +4 to +11 percentage points across the swept models.
SLM-SS is proposed, a token-based generative speech separation framework that models multi-talker mixtures with speech language models and introduces a per-talker non-autoregressive strategy that simplifies high-order modeling and improves the stability.
This work presents Relay, a hybrid framework that uses an LLM to derive and validate deterministic repair rules from representative failures, reuses them without model calls, and escalates cases unresolved by rules to a per-case agent.
3D Human Pose Estimation (3D HPE) is used in indoor environments, such as smart homes, to analyze human movement and monitor human states. Millimeter-wave (mmWave) radar is suitable for this task because it is robust to lighting variations and does not capture images of human appearance. However, radar observations oft...
P perturbation concentration is established as a complementary, model- and attack-dependent axis of $\ell_1$ attack evaluation, and direct in-loop constrained optimization preserves up to $88$ percentage points more attack success than post-hoc clipping, highlighting the importance of constraint enforcement.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
