We have 7 of 78 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.
Existing large language model (LLM) based multi-agent systems have been shown to scale poorly, and we identify three problems: reading burden that grows with the group, useful information diluted by shared work of unknown quality, and fragility to failed agents. We argue that the problems are largely due to agent-centr...
Despite rapid progress in automating scientific research, generating promising and well grounded research solutions remains a central challenge. We isolate research ideation as a standalone task and build our solution on the intuition that a challenge in one field can often be addressed by a mechanism that solved an an...
Context Language Models are introduced, language models that natively manage their own context and can be steered with natural-language instructions evolved through a standard skill-optimization loop, improving held-out accuracy by up to 35.9 points on a context-management task while reducing compute.
This work introduces ConfQA, a fine-tuning strategy that reduces hallucination rates from 20-40% to below 5% across multiple factuality benchmarks, and proposes ConfRAG, a triggering strategy that invokes RAG only when the model responses with unsure.
Switch Distillation is proposed, a simple mid-training objective that distills on tokens where the teacher is confident, using teacher predictive entropy as a lightweight routing signal, and otherwise falls back to cross-entropy, which consistently outperforms existing distillation objectives across teacher sizes.
Anchored Decoding is proposed, a plug-and-play inference-time method for suppressing verbatim copying that enables decoding from any risky LM trained on mixed-license data by keeping generation in bounded proximity to a permissively trained safe LM.
This work introduces S-EMBER (Streaming Egocentric Memory Benchmark for Episodic Retrieval), a large-scale benchmark comprising 3,141 videos totaling 388 hours of organic activity captured via Ray-Ban Meta smart glasses that establishes a hardware-authentic foundation for developing grounded, reliable episodic memory i...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
