We have 5 of 29 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
GoiBERT, a family of two compact Vietnamese encoders with 26M and 49M parameters that operate directly on raw text, shows that compression is nearly lossless for sentiment and classification tasks but remains costly for inference and entity recognition, which points to clear directions for future work.
StreamFraudNet is introduced, which processes incoming audio through overlapping bounded-context windows using a frozen self-supervised speech encoder, recurrent temporal modeling, and learned aggregation of latent window scores to demonstrate that fraud risk can be scored incrementally from raw speech without transcri...
Results clarify when causal cross-query memory improves repair and when broader memory representations remain preferable, and show that negative memory contributes modestly, the value of type conditioning and lexical-dense ranking is dataset dependent, and schema-local experience provides the most consistent benefit.
A tree-structured framework is proposed that organizes failures in knowledge-intensive visual question answering into model-specific operational outcomes that support attribution-guided routing to targeted interventions, including image repair, entity support, question rewriting, and factual evidence.
Text-compatible JEPA objectives must preserve multiple plausible completions rather than compress them into a single latent point, showing that text-compatible JEPA objectives must preserve multiple plausible completions rather than compress them into a single latent point.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
