Category
6,756 papers
GMAE aggregates reward realizations across possible contexts into a response-level distribution and estimates expected advantages, which exhibits stable learning, low extra cost, and good applicability across training datasets and RL backbones.
It is revealed that multi-turn interaction causes widespread performance degradation, incurring relative performance drops of up to 21% and increasing unreliability by 47%, making RAG systems simultaneously less accurate and less reliable.
Inspired by long-term memory in human listening, Long-Term Memory-Guided Audio Enhancement (LTM-AE) is proposed to improve selective target perception by refining the audio representations of ALLMs without training to improve selective target perception.
DraftTrace is introduced, a writing environment that jointly captures three complementary views of writing: the final product, the writing process and interactions with an integrated AI-assistant.
Reach audiences
Advertise in front of researchers, engineers, and readers.
It is found that compression degrades reliability before solvability and proposed PAIR (Prompt Adaptation using Interventional Rollouts) for adapting structured compression prompts achieves the strongest cross-run reliability among compressed methods in every main benchmark-scope combination.
The findings go against current endeavors of defining, identifying, and targeting general intelligence as a tangible construct in language model development, since the strategy of targeting a single conceptual ability without support is left without support.
Cross-modal associations are systematic pairings of features across modalities, such as the association of'bouba'with round shapes and'kiki'with sharp shapes. Prior work has compared humans and vision-language models (VLMs) on such associations, but often using different stimuli or tasks between humans and models. Here...
Masked diffusion language models (MDLMs) can generate text efficiently by predicting multiple masked tokens in parallel, but predictions from the same forward pass are not necessarily reliable when committed together. We study when parallel commitment is reliable. Our diagnostics show that confidence alone does not det...
Decision-only language models return a probability for every answer option instead of generating text, which makes them attractive as survey respondents and as judges. We audit the cultural values of one such model, TypeSafe's JEV, with the Values Survey Module 2013. We asked it the 24 items as 12 matched Saudi and 12...
Verbalization training is introduced, a method for making LLMs less reticent about verbalizing evaluation awareness while avoiding to supervise the latent belief itself, and it is shown that VT-induced verbalizations reflect the richer knowledge acquired by the model.
Mixture-of-Experts (MoE) layers are central to frontier language models, and recent architectures push toward more and smaller experts. In this regime, the standard linear router becomes a bottleneck: with $M$ experts and hidden dimension $h$, its per-token cost $\Theta(Mh)$ dominates the MoE layer once $M$ is large. W...
A three-stage symbolic reasoning circuit (abstraction, induction, retrieval) is traced across shot counts in three model families and finds it is detectable and functional well before the model achieves high accuracy.
A new language-processing tool could help identify the highest-risk individuals from natural language, enabling swifter interventions.
A Blog post by Liquid AI on Hugging Face
Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking are our most advanced live dialogue models yet, built for natural conversation.
A new method, called CW-Net, translates the reasoning process of an autonomous vehicle’s AI system into understandable concepts that explain its behavior.
With millions of users across the world, Julia has been used to conduct cutting-edge research and to design new drugs, jet engines, heat pumps, and more.
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.
