AI Papers of the Week
Every paper worth reading in AI, hand-picked one week at a time.
Dobb-E
NYU's Dobb-E is an affordable household-manipulation robot that learns new tasks with just 5 minutes of user demonstrations.
Translatotron 3
Google's Translatotron 3 performs speech-to-speech translation using only monolingual data - no parallel corpora required.
System 2 Attention (S2A)
Meta's S2A uses the LLM's own reasoning to decide what context actually matters, regenerating a clean prompt before the final response step.
Advancing Long-Context LLMs
A survey of methodologies for improving Transformer long-context capability across pretraining, fine-tuning, and inference stages.
Parallel Speculative Sampling
Amazon researchers propose a parallel variant of speculative sampling that achieves significant LLM inference speedups with minimal extra parameters.
Mirasol3B
Google's Mirasol3B is a multimodal model that decouples modalities into focused autoregressive components rather than forcing a single fused stream.
Teaching Small LMs to Reason
An approach that teaches smaller language models to explicitly select among reasoning techniques for each problem.
GPQA
A graduate-level Google-proof QA benchmark designed to stress-test reasoning in systems that might exceed human expertise.
Hitchhiker's Guide From CoT to Agents
A survey mapping the conceptual evolution from chain-of-thought reasoning to modern language-agent frameworks.
GAIA
Meta's GAIA is a benchmark for general AI assistants that requires reasoning, multimodal handling, web browsing, and tool use to solve real-world questions.
MedAgents
A collaborative multi-round framework for medical reasoning that uses role-playing LLM agents to improve accuracy and reasoning depth.
TÜLU 2
Allen AI's TÜLU 2 is a suite of improved open instruction-tuned LLMs and an accompanying study of adaptation best practices.
Emu Video and Emu Edit
Meta releases Emu Video and Emu Edit, a pair of diffusion models targeting controlled text-to-video generation and instruction-based image editing.
Chain-of-Note (CoN)
Tencent's Chain-of-Note adds an explicit note-taking step to RAG so the model can evaluate retrieved evidence before answering.
LLMs for Scientific Discovery
A broad evaluation of GPT-4 across scientific disciplines including drug discovery, biology, and computational chemistry.
Fine-Tuning LLMs for Factuality
Stanford fine-tunes LLMs for factuality without any human labels by using automatically generated preference signals.
Contrastive Chain-of-Thought
Proposes contrastive CoT prompting where models see both valid *and* invalid reasoning demonstrations to reduce reasoning errors.
Survey on Language Models for Code
A comprehensive survey of LLMs for code covering 50+ models, 30+ evaluation tasks, and 500 related works.
JARVIS-1
An open-world multimodal agent for Minecraft that combines perception, planning, and memory into a self-improving system.
Learning to Filter Context for RAG (FILCO)
CMU's FILCO improves RAG by training a dedicated model to filter retrieved contexts before they reach the generator.
MART (Multi-round Automatic Red-Teaming)
Meta's MART scales LLM safety alignment using fully automatic multi-round red-teaming.
LLMs Can Deceive Users (Trading Agent)
Apollo Research shows that a helpful, honest LLM stock-trading agent can spontaneously deceive users under pressure.
Hallucination in LLMs Survey
A comprehensive survey of hallucination in LLMs, covering taxonomy, causes, evaluation, and mitigation.
Simplifying Transformer Blocks
Researchers show that many components of the standard transformer block can be removed with no loss in training speed or quality.