Search papers, labs, and topics across Lattice.
LLMs can be trained to negotiate like expert agents, extracting significantly higher surpluses by strategically exploring buyer markets rather than fixating on immediate bids.
Low diversity in training data can lead to substantial performance drops in language models, revealing a critical oversight in data augmentation practices.
User ratings of LLMs are more about what users expect than the actual performance, revealing a critical flaw in how we assess AI models.
Cross-lingual exploration can unlock hidden knowledge in LLMs, improving factual recall and consistency across 17 languages.
Turn-final words are not just longer; they provide a crucial prosodic cue for predicting conversational turns, localized mainly in the final syllable.
Optimizing input configurations can boost LLM performance in pathology tasks, closing the gap with specialized models and challenging assumptions about domain-specific training.
State inertia in full-duplex spoken language models can lead to missed user input, but activation steering effectively mitigates this issue, boosting comprehension rates significantly.
Routine encounter metadata can lead to alarming rates of sensitive diagnosis recovery in medical language models, revealing significant privacy risks.
Current clinical AI systems often neglect the temporal dimension of patient care, limiting their effectiveness in longitudinal reasoning.
Multimodal pretraining doesn't guarantee better alignment with human reading patterns, suggesting that language-internal representations are still king when modeling how humans process text.
Subword tokenization just got a whole lot more efficient: ToaST slashes token counts by 11% and boosts language model performance by up to 7.6% compared to standard methods.
LLMs trained with Vector Policy Optimization (VPO) learn to produce diverse solutions that unlock previously unsolvable problems in evolutionary search, outperforming models optimized for single scalar rewards.
LMs encode grammaticality as a distinct feature in their hidden representations, separable from raw string probability and generalizable across languages.
Imagine a workspace that subtly shifts lighting and sound to match your mood, all powered by an LLM that understands your needs – this paper explores the potential and pitfalls of that reality.
Forget complex fixed-point machinery: this work offers a dramatically simpler and more efficient route from external regret to $Φ$-regret minimization.
Cyclic equalizability, a concept relevant to card-based cryptography, boils down to having identical Parikh vectors.
Organizational AI's biggest bottleneck isn't finding the right information, but knowing what's actually true, agreed upon, or even known at all.
Gaze-tracking unlocks a new level of personalized AI assistance, enabling LLMs to infer user cognitive states and boost recall performance.
Training superword tokenizers just got 600x faster, unlocking practical use of subword tokenization across pre-tokenization boundaries.
LLM agents can autonomously outperform fixed evolutionary search by 3-10x on open-ended discovery tasks when given persistent memory, asynchronous collaboration, and heartbeat-based interventions.
Demystifying LLMs for the masses might be as simple as turning their mechanics into a game.
Particle filter models of sentence processing inherently predict "digging-in" effects—where disambiguation difficulty increases with the length of the ambiguous region—a phenomenon not captured by surprisal-based models.
Fine-tuning unlocks LLMs' surprising ability to predict how memorable a sentence is and how long it takes to read, exceeding traditional methods.
Scale qualitative analysis of educational discourse data without sacrificing rigor using a mixed-initiative system that orchestrates LLMs and human expertise.
NeuroSkill(tm) offers real-time, edge-based human-AI interaction by directly modeling human state of mind from BCI data, enabling more nuanced and empathetic agentic responses.
Feminist participatory annotation workshops reveal the nuanced tensions between contextual richness, pluralism, and the practical need for bounded consensus in AI data work.
