ORPO performs preference alignment during supervised fine-tuning via a monolithic odds ratio penalty, allowing 7B models to outperform larger state-of-the-art models on alignment benchmarks.
Title resolution pending
22 Pith papers cite this work. Polarity classification is still indexing.
22
Pith papers citing it
citation-role summary
dataset 1
method 1
citation-polarity summary
representative citing papers
PROTEA supplies an offline interface for scoring intermediate outputs in multi-agent LLM workflows, performing backward evaluation from final answers, and iterating on targeted prompt revisions with visible score changes.
FedCoLLM is a parameter-efficient federated co-tuning framework that improves client SLMs via server LLMs and enriches LLMs with client domain insights using adapters on NLP text generation tasks.
Refusal in language models is mediated by a single direction in residual stream activations that can be erased to disable safety or added to elicit refusal.
Experiments across code LLMs show no-review collapses fastest, human-gated filters slow collapse, and AI self-gates lose effect over time, degenerating to ungated self-training under self-confirming acceptance as proven via gated distributional reweighting and spectral analysis.
MINCE shrinks IFEVAL by 54%, MMLU by 89%, and GSM8K by 70% via few-model Monte Carlo calibration while keeping maximum drift at or below 2.62 percentage points.
PoE-Bridge uses a product-of-experts bridge between diffusion and autoregressive distributions, with DLM drafting plus rejection and importance sampling, to deliver 5x speedup over standard DLM decoding while recovering at least 95% of AR performance on math and coding tasks.
MLP activations measured as massive activations or first four moments correlate weakly (max |Spearman| = 0.33) with in-context example quality across Llama-3.2-3B, Qwen2.5-3B, and multiple classification/generative tasks, so activation-based active learning should not be used for ICL.
Empirical update to prior work shows most of 20 recent Transformer modifications do not transfer at 1-3B scales when measured with downstream CLIMB-12 tasks, multi-seed noise floor, and cross-scale stability.
ZAYA1-8B is a reasoning MoE model with 700M active parameters that matches larger models on math and coding benchmarks and reaches 91.9% on AIME'25 via Markovian RSA test-time compute.
REGLU guides LoRA-based unlearning via representation subspaces and orthogonal regularization to outperform prior methods on forget-retain trade-off in LLM benchmarks.
Cross-model semantic disagreement adds an epistemic uncertainty term that improves total uncertainty estimation over self-consistency alone, helping flag confident errors in LLMs.
LLMs resist low-frequency permanent GPU faults but certain datapaths and precision formats trigger catastrophic training divergence even at moderate fault rates.
MM1 models achieve state-of-the-art few-shot multimodal results by pre-training on a careful mix of image-caption, interleaved, and text-only data with optimized image encoders.
FedProxy replaces weak adapters with a proxy SLM for federated LLM fine-tuning, outperforming prior methods and approaching centralized performance via compression, heterogeneity-aware aggregation, and training-free fusion.
NVIDIA releases the Nemotron 3 model family with hybrid Mamba-Transformer architecture, LatentMoE, NVFP4 training, MTP layers, and multi-environment RL post-training for reasoning and agentic tasks.
Introduces Tree Generation (TG-SFT) to generate synthetic instruction-tuning data from LLMs, reducing catastrophic forgetting when fine-tuning MLLMs on domain-specific or multimodal data.
ZONOS2 8B is a scaled MoE TTS model with 900M active parameters trained on 6M hours of data that reports competitive SOTA results on naturalness, speaker similarity, WER, and a new ZTTS1-Eval benchmark while releasing weights and code.
Qwen2.5-3B was continued-pretrained and then fine-tuned with rsLoRA r256 on Sardinian data to reach 28.5 BLEU into the language, outperforming full fine-tuning and other LoRA variants.
Step-Video-T2V describes a 30B-parameter text-to-video model with custom Video-VAE, 3D DiT, flow matching, and Video-DPO that claims state-of-the-art results on a new internal benchmark.
Workplace agent success on WorkBench rose from 43% to 98% over two years with sharply reduced harmful actions.
A tutorial synthesizing foundations, recent models such as PALO and Maya, and low-cost methods for tri-modal multilingual AI in resource-constrained settings.
citing papers explorer
No citing papers match the current filters.