We study a persistent failure mode in multi-objective alignment for large language models (LLMs): training improves performance on only a subset of objectives w...
Multi-turn jailbreaks capture the real threat model for safety-aligned chatbots, where single-turn attacks are merely a special case. Yet existing approaches br...
A central question in cognitive science is whether conceptual representations converge onto a shared manifold to support generalization, or diverge into orthogo...
Ambiguity poses persistent challenges in natural language understanding for large language models (LLMs). To better understand how lexical ambiguity can be reso...
Autoregressive large language models (LLMs) deliver strong performance but require inherently sequential decoding, leading to high inference latency and poor GP...
Memory is increasingly central to Large Language Model (LLM) agents operating beyond a single context window, yet most existing systems rely on offline, query-a...
Existing techniques for accelerating language model inference, such as speculative decoding, require training auxiliary speculator models and building and deplo...
Large language models (LLMs) are increasingly being used in a zero-shot fashion to assess mental health conditions, yet we have limited knowledge on what factor...
Speech Emotion Recognition (SER) research has faced limitations due to the lack of standard and sufficiently large datasets. Recent studies have leveraged pre-t...
Diffusion large language models (dLLMs) have emerged as a promising alternative for text generation, distinguished by their native support for parallel decoding...
Deep research agents have emerged as powerful systems for addressing complex queries. Meanwhile, LLM-based retrievers have demonstrated strong capability in fol...
Semantic representations can be framed as a structured, dynamic knowledge space through which humans navigate to retrieve and manipulate meaning. To investigate...
