Category
6,313 papers
The results show that compact fine-tuned models can preserve most extraction accuracy, but model selection must account for prompt choice, throughput, and serving-stack behavior.
This article offers a framework for transitioning from rigid execution pipelines to adaptive, intelligent computational environments, broadly applicable across distributed environments, they are particularly tailored to the resource-intensive throughput demands of modern computational biology.
A dataset of 164 expert-annotated progress chains from the MIT PRIMES--Art of Problem Solving CrowdMath program (2016-2025), a collaborative research initiative whose discussions have led to peer-reviewed publications, is introduced.
Retrospective Harness Optimization is introduced, a self-supervised method that optimizes the agent harness using only past trajectories and alters the agent's behavior patterns and sustains higher accuracy during long-horizon sessions.
Reach audiences
Advertise in front of researchers, engineers, and readers.
DASH is introduced, which supervises the conditional and unconditional branches independently and an anchor term regularises the conditional prediction toward ground-truth noise, and the teacher's final learned per-timestep curriculum transfers into the student as a frozen prior.
TIGER is presented, an inference-time framework that redesigns feedback for localized repair that reduces unsupported content while preserving task quality and a CrisisFACTS case study suggests that the same repair mechanism can improve grounding in multi-source settings.
This study formalizes Autonomous Agentic Data Engineering, a novel task designed to evaluate LLMs as autonomous data engineers that drive model specialization through end-to-end data curation, and charts a path toward agent-driven model specialization.
To make CBM measurable, BeliefTrack is introduced, a closed-world benchmark spanning Rule Discovery and Circuit Diagnosis, where a finite belief space and symbolic verifiers enable exact turn-level evaluation.
This paper presents a method for aggressively pruning experts from modern mixture-of-experts LLMs while incurring negligible degradation in translation quality, and shows that translation requires only a fraction of the LLM, enabling substantial compression of the MoE blocks that contain over 90% of parameters.
A taxonomy of CoT is proposed consisting of Explicit CoT, which outputs all operations without aggregation, Composed CoT, which combines multiple operations into a single step, and Implicit CoT, which omits intermediate operations.
The Unlearning Depth Score (UDS), a metric that quantifies the mechanistic depth of unlearning via activation patching, is introduced, confirming the causal approach as the most reliable for unlearning evaluation.
FinCAD is proposed, an inference-time adaptation of Context-Aware Decoding that attenuates contributions from memorised historical outcomes without retraining and raises the subset-averaged in-sample/out-of-sample Spearman correlation on an eleven-model leaderboard.
Machine Intelligence
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
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.
