Category
3,445 papers
Endpoint accuracy on abstract-reasoning benchmarks does not reveal whether a language model has acquired a transferable rule or fit distribution-specific regularities. We study this distinction in small language models on the ARC-TGI benchmark, which organizes abstract grid transformations into controllable task famili...
We ask whether specific attention heads, and more finely specific neurons inside those heads, are responsible for recognizing that a language model's context contains network infrastructure information (a hostname paired with its IP address), and whether that responsibility can be validated causally rather than by corr...
Low-rank quantization error compensation (LQEC) recovers the accuracy lost under aggressive weight quantization by attaching a closed-form rank-$r$ adapter beside each frozen quantized weight, without any training. We show that existing compensators are limited by two shared simplifications. They calibrate symmetricall...
Model merging offers a promising solution for combining multiple fine-tuned checkpoints into a single model through parameter arithmetic. However, finding optimal merging coefficients requires an extensive search that becomes prohibitively expensive as models scale in both size and number, due to high memory requiremen...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Autoregressive large language models (LLMs) have rapidly advanced in capability, but their increasing scale comes with substantial computational and memory costs at inference time. Knowledge distillation (KD) offers a practical solution by transferring knowledge from a large teacher model to a smaller student model via...
This work proposes GRADE (GRadient-Aligned Data-centric rEcipe), a data-centric framework combining two mechanisms: a state-aware selector that continually admits samples aligned with the evolving multi-task gradient field, and a self-calibrating step-level gate that rejects updates likely to cause destructive overwrit...
This paper characterize the interaction between mismatch and the policy-gradient direction, distinguishing locally amplifying from contracting update contributions that mismatch magnitude alone cannot identify and introduces TRIAGE, a direction-aware stabilization method that uses segment-level diagnosis to selectively...
RoMod is proposed, an efficient VAD framework trained with only \(5\%\) of weakly labeled videos that achieves state-of-the-art performance while running substantially faster than dense backbones of comparable size.
It is argued nested model-selection protocols should be standard when probing encoder layer representations on small clinical speech datasets, and a fair comparison across representation families identifies a compact, task-aligned affect--prosody model as competitive with substantially more complex SSL, deep-learning,...
To formulate real-world remote sensing restoration as a traceable trajectory, EORestore-Agent is presented, which replaces this unmeasurable objective with reference-free, verifiable per-step decisions.
Experiments demonstrate that LensDistill substantially improves fine-grained object captioning while preserving existing grounding and scene-level QA performance, and establish the feasibility of transferring externally acquired fine-grained knowledge into native 3D LLMs.
This work studies idealized optimizers geometries in continuous time to model small-step training in deep learning and characterize a region where majority losses are optimized regardless of the admissible minority structure.
A Blog post by IBM Granite on Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Gemini 4 Carbon is our strongest model with state-of-the-art cybersecurity and long horizon capabilities.
A Blog post by Liquid AI on Hugging Face
Genie 4: our new world model unlocking unprecedented realism in real-time simulation.
Generative AI
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
