Search papers, labs, and topics across Lattice.
10 papers from Meta AI (FAIR) on Reasoning & Chain-of-Thought
Achieving near-autoregressive accuracy while boosting decoding speed by over 2.4 times could redefine efficiency benchmarks in generative reasoning tasks.
Clinically structured rank allocation in BiRG-LoRA boosts medical question answering accuracy while reducing trainable parameters by over 28%.
Reasoning-aware retrieval can boost language model performance by surfacing diverse solution strategies that traditional methods overlook.
Feedback Distillation boosts reasoning model performance by enhancing trajectory diversity and policy entropy, outperforming traditional methods like GRPO.
Forget task-specific fine-tuning – teaching VLMs basic geometry yields a +29% boost on spatial reasoning benchmarks.
AI could provide a new lens on the structure of mathematics, potentially answering the age-old question of whether it is discovered or invented.
LLMs can now infer plausible stage layouts from unstructured text alone, opening up new possibilities for automated media production.
LLM reasoning research is inadvertently paving a dangerous path towards AI situational awareness and strategic deception, demanding a re-evaluation of current safety measures.
LLMs can ace math problems while reasoning like a drunk toddler, with 82% of correct answers arising from unstable, inconsistent logic.
By surgically intervening in MLLM decoding, this work cuts hallucination rates without sacrificing descriptive quality, a feat prior methods struggled to achieve.
