Derives geodesic ridge regularization and Riemannian Gibbs Process prior for feature-learning wide neural networks, generalizing kernel-regime results via function-space axiomatization.
super hub Mixed citations
DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
Mixed citation behavior. Most common role is background (62%).
170
Pith papers citing it
Background
62% of classified citations
abstract
As Transfer Learning from large-scale pre-trained models becomes more prevalent in Natural Language Processing (NLP), operating these large models in on-the-edge and/or under constrained computational training or inference budgets remains challenging. In this work, we propose a method to pre-train a smaller general-purpose language representation model, called DistilBERT, which can then be fine-tuned with good performances on a wide range of tasks like its larger counterparts. While most prior work investigated the use of distillation for building task-specific models, we leverage knowledge distillation during the pre-training phase and show that it is possible to reduce the size of a BERT model by 40%, while retaining 97% of its language understanding capabilities and being 60% faster. To leverage the inductive biases learned by larger models during pre-training, we introduce a triple loss combining language modeling, distillation and cosine-distance losses. Our smaller, faster and lighter model is cheaper to pre-train and we demonstrate its capabilities for on-device computations in a proof-of-concept experiment and a comparative on-device study.
hub tools
citation-role summary
background 18
method 11
citation-polarity summary
claims ledger
- abstract As Transfer Learning from large-scale pre-trained models becomes more prevalent in Natural Language Processing (NLP), operating these large models in on-the-edge and/or under constrained computational training or inference budgets remains challenging. In this work, we propose a method to pre-train a smaller general-purpose language representation model, called DistilBERT, which can then be fine-tuned with good performances on a wide range of tasks like its larger counterparts. While most prior work investigated the use of distillation for building task-specific models, we leverage knowledge di
authors
co-cited works
representative citing papers
Adaptive scheduling of interventions in discrete diffusion language models, timed to attribute-specific commitment schedules discovered with sparse autoencoders, delivers precise multi-attribute steering up to 93% strength while preserving generation quality.
A classifier trained only on transformer fine-tuning data detects an invariant memorization signature that transfers to Mamba, RWKV-4, and RecurrentGemma with AUCs of 0.963, 0.972, and 0.936.
Tiny language models under 10M parameters trained on a synthetic children's story dataset generate fluent, consistent, multi-paragraph English text with near-perfect grammar and reasoning.
GPT-3 shows that scaling an autoregressive language model to 175 billion parameters enables strong few-shot performance across diverse NLP tasks via in-context prompting without fine-tuning.
Face-Feature Tuning is a label-free logit remapping method that reduces FPR/TPR gaps across groups in deepfake detection while preserving overall accuracy.
Introduces (ε,q,t,A)-behavioral indistinguishability and shows via Qwen/Llama experiments that LoRA distillation boosts semantic similarity but leaves detectable behavioral differences under adversarial evaluation.
PHAT-JeT combines geometric message-passing with hierarchical patch attention to reach state-of-the-art accuracy and background rejection among resource-constrained jet tagging models on four benchmarks.
CROC constructs finite-sample valid confidence sets for the root-cause index in multi-stream change detection using conformal p-values under independence and exchangeability assumptions.
Layer-wise Token Compression applies adaptive token pooling at middle transformer layers for cross-encoder rerankers, preserving MS MARCO ranking quality while raising QPS up to 25% on passages and 116% on documents, with added gains on listwise LLM rerankers and a regularizer effect for long inputs
TIDAL recovers temporal phase signals from LLM-derived semantics of provisioning metadata to enable complementary CVD placement, reducing overload frequency by 79.1% on production traces.
RISE is an inference-time semantic reranking framework that refines low-confidence predictions in rhetorical role labeling using contrastively learned label representations, delivering an average +9.15 macro-F1 gain on hard examples across eight datasets and seven models.
DMP-MH clips degrees to control triangle sensitivity, synthesizes an edge-DP graph with Noisy Mirror Descent, and distills it into dual-stream hash networks, beating private baselines by up to 11.4 mAP on MIRFlickr-25K and NUS-WIDE while keeping 92.5% of non-private performance.
Foundation model priors amplify worst-client disparity under extreme federated heterogeneity, creating a fairness paradox where larger models perform worse for disadvantaged clients.
Switchcraft routes agentic tool-calling queries to the lowest-cost model that preserves correctness, reaching 82.9% accuracy and 84% cost reduction on five benchmarks.
TRACE creates valid conformal prediction sets for complex generative models by scoring outputs via averaged denoising or velocity errors along stochastic transport paths instead of likelihoods.
Presents MBFC-2025 dataset and multi-view embeddings with fusion methods for media bias and factuality, reporting SOTA results on ACL-2020 and new benchmarks on MBFC-2025.
VOW formulates LLM watermark detection as a secure two-party computation using a Verifiable Oblivious Pseudorandom Function to achieve private and cryptographically verifiable detection.
A single end-to-end Transformer model unifies stellar labels from heterogeneous spectroscopic surveys into a self-consistent scale without post-hoc recalibration.
AgentPulse is a continuous multi-signal framework that scores AI agents on benchmark performance, adoption, sentiment and ecosystem health, showing these factors are complementary and that benchmark-plus-sentiment predicts external adoption metrics.
RoLegalGEC is the first Romanian legal-domain dataset for grammatical error detection and correction, consisting of 350,000 examples, with evaluations of several neural models.
Open-source LLMs detect phishing intent at high rates but still generate actionable phishing content, and GuardPhish supplies a dataset plus modular classifiers to close the gap.
DepthVAR adaptively allocates per-token computational depth in VAR models using a cyclic rotated scheduler and dynamic layer masking to achieve 2.3-3.1x inference speedup with minimal quality loss.
SecureRouter accelerates secure transformer inference by 1.95x via an encrypted router that selects input-adaptive models from an MPC-optimized pool with negligible accuracy loss.
citing papers explorer
-
BoolXLLM: LLM-Assisted Explainability for Boolean Models
BoolXLLM augments an existing Boolean rule learner with LLMs for feature selection, discretization thresholds, and natural-language rule translation to improve interpretability while preserving accuracy.
-
Unified Approach for Weakly Supervised Multicalibration
A unified framework uses contamination-matrix risk rewrites and witness-based calibration constraints to estimate and correct multicalibration under weak supervision, providing finite-sample guarantees and the WLMC post-hoc recalibration algorithm.
-
Rethinking Dense Sequential Chains: Reasoning Language Models Can Extract Answers from Sparse, Order-Shuffling Chain-of-Thoughts
Reasoning language models extract answers from sparse, order-shuffled chain-of-thought traces with little accuracy loss.
-
Experience Sharing in Mutual Reinforcement Learning for Heterogeneous Language Models
Mutual Reinforcement Learning allows heterogeneous LLMs to exchange experience through mechanisms like Peer Rollout Pooling, Cross-Policy GRPO Advantage Sharing, and Success-Gated Transfer, with outcome-level sharing identified as favorable on the stability-support trade-off.
-
Patch-Effect Graph Kernels for LLM Interpretability
Patch-effect graphs built from causal mediation, partial correlation, and co-influence, when analyzed with graph kernels, preserve task-discriminative signals from activation patching that outperform global shape descriptors and raw baselines on GPT-2 Small.
-
DiBA: Diagonal and Binary Matrix Approximation for Neural Network Weight Compression
DiBA factors weight matrices into diagonal-binary-diagonal-binary-diagonal form to cut matrix-vector multiplies from mn to m+k+n operations and improves accuracy on DistilBERT and audio transformer tasks after replacement.
-
LEAP: Layer-wise Exit-Aware Pretraining for Efficient Transformer Inference
LEAP adds a layer-wise exit-aware constraint to standard distillation, reconciling it with early-exit mechanisms and delivering 1.61x wall-clock speedup on MiniLM at 0.95 threshold with 91.9% early exits by layer 7.
-
Reliable Answers for Recurring Questions: Boosting Text-to-SQL Accuracy with Template Constrained Decoding
TeCoD improves Text-to-SQL execution accuracy by up to 36% over in-context learning and cuts latency 2.2x on matched queries by extracting templates from historical pairs and enforcing them with constrained decoding.
-
PiLLar: Matching for Pivot Table Schema via LLM-guided Monte-Carlo Tree Search
PiLLar is the first LLM-guided Monte-Carlo Tree Search framework for joint schema-value matching on pivot tables, achieving 87.94% average accuracy on a new benchmark PTbench derived from real-world domains.
-
ImproBR: Bug Report Improver Using LLMs
ImproBR combines a hybrid detector with GPT-4o mini and RAG to raise bug report structural completeness from 7.9% to 96.4% and executable steps from 28.8% to 67.6% on 139 Mojira reports.
-
IAM: Identity-Aware Human Motion and Shape Joint Generation
IAM jointly synthesizes motion sequences and body shape parameters conditioned on multimodal identity signals to achieve more realistic and identity-consistent human motions.
-
ADE: Adaptive Dictionary Embeddings -- Scaling Multi-Anchor Representations to Large Language Models
ADE scales multi-anchor word representations to transformers via Vocabulary Projection, Grouped Positional Encoding, and context-aware reweighting, achieving 98.7% fewer trainable parameters than DeBERTa-v3-base while matching or exceeding it on two text-classification benchmarks and compressing the
-
RouteNLP: Closed-Loop LLM Routing with Conformal Cascading and Distillation Co-Optimization
RouteNLP is a closed-loop LLM routing framework using conformal cascading and distillation co-optimization that cut inference costs by 58% in an 8-week enterprise deployment while preserving 91% acceptance and high quality on benchmarks.
-
GRASPrune: Global Gating for Budgeted Structured Pruning of Large Language Models
GRASPrune removes 50% of parameters from LLaMA-2-7B via global gating and projected straight-through estimation, reaching 12.18 WikiText-2 perplexity and competitive zero-shot accuracy after four epochs on 512 calibration sequences.
-
Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
On-policy distillation works when student and teacher models share thinking patterns and the teacher adds new capabilities, with success tied to alignment on a small set of high-probability tokens.
-
BiSpikCLM: A Spiking Language Model integrating Softmax-Free Spiking Attention and Spike-Aware Alignment Distillation
BiSpikCLM is the first fully binary spiking MatMul-free causal language model that matches ANN performance on generation tasks using only 4-6 percent of the compute via softmax-free spiking attention and spike-aware distillation.
-
Chain-of-Models Pre-Training: Rethinking Training Acceleration of Vision Foundation Models
CoM-PT trains vision foundation models in ascending size order using inverse knowledge transfer, allowing larger models to achieve superior performance with significantly reduced overall computational cost compared to individual training.
-
A Little Rank Goes a Long Way: Random Scaffolds with LoRA Adapters Are All You Need
Frozen random backbones with low-rank LoRA adapters recover 96-100% of fully trained performance on diverse architectures while training only 0.5-40% of parameters.
-
LOLGORITHM: Funny Comment Generation Agent For Short Videos
LOLGORITHM is a modular multi-agent system for generating stylized funny comments on short videos that achieves 80-84% human preference over baselines on YouTube and Douyin datasets.
-
A Comparative Study of Semantic Log Representations for Software Log-based Anomaly Detection
QTyBERT matches or exceeds BERT-based log anomaly detection effectiveness while reducing embedding generation time to near static word embedding levels.
-
LaScA: Language-Conditioned Scalable Modelling of Affective Dynamics
A framework converts interpretable facial and acoustic features into language descriptions, feeds them to a pretrained LM for semantic embeddings, and uses those embeddings as priors to improve valence and arousal change prediction on Aff-Wild2 and SEWA while remaining transparent.
-
Beyond End-to-End: Dynamic Chain Optimization for Private LLM Adaptation on the Edge
ChainFed achieves memory-efficient private LLM fine-tuning on edge devices through sequential layer-by-layer adapter training with dynamic co-tuning, perceptive optimization, and adaptive starting point selection, improving accuracy by up to 46.46%.
-
ExpressMM: Expressive Mobile Manipulation Behaviors in Human-Robot Interactions
ExpressMM integrates high-level language-guided planning with low-level vision-language-action policies to enable expressive and interruptible mobile manipulation behaviors in human-robot collaboration, shown effective in an assembly task via audience evaluations.
-
CLIP-RD: Relative Distillation for Efficient CLIP Knowledge Distillation
CLIP-RD adds VRD for cross-modality distillation consistency and XRD for bidirectional cross-modal symmetry to align student embedding geometry more closely with the teacher, yielding a 0.8 percentage point gain over prior distillation methods.
-
Dual-Space Knowledge Distillation with Key-Query Matching for Large Language Models with Vocabulary Mismatch
The authors introduce DSKD-CMA-GA using generative adversarial learning to fix key-query distribution mismatches in cross-tokenizer knowledge distillation, reporting modest average ROUGE-L gains of 0.37 especially on out-of-distribution data.
-
Learning to Assist: Physics-Grounded Human-Human Control via Multi-Agent Reinforcement Learning
AssistMimic is the first multi-agent RL method that successfully tracks assistive human-human interaction motions in simulation by using partner-aware policies, single-agent initialization, dynamic reference retargeting, and contact-promoting rewards.
-
Don't Ignore the Tail: Decoupling top-K Probabilities for Efficient Language Model Distillation
A modified divergence decouples top-K teacher probabilities from the distribution tail during distillation, yielding competitive performance on decoder models with standard compute.
-
Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation
Generalized on-policy distillation with reward scaling above one (ExOPD) lets student models surpass teacher performance when merging domain experts on math and code tasks.
-
SCOUT: A Defense Against Data Poisoning Attacks in Fine-Tuned Language Models
SCOUT uses token saliency analysis to detect both standard and contextually-plausible backdoor attacks in language models while maintaining clean accuracy.
-
Gradient-descent methods for scalable quantum detector tomography
Gradient descent optimization reconstructs POVMs for phase-insensitive quantum detectors with higher or comparable fidelity to constrained convex optimization but in much less time.
-
You Had One Job: Per-Task Quantization Using LLMs' Hidden Representations
TAQ estimates per-layer importance from hidden representations and output sensitivity on task calibration data to allocate mixed precision in a training-free PTQ setting, outperforming task-agnostic baselines on accuracy-memory ratio across benchmarks.
-
A Metamorphic Testing Perspective on Knowledge Distillation for Language Models of Code: Does the Student Deeply Mimic the Teacher?
Student models distilled from code language models often fail to deeply mimic teachers, showing up to 62% behavioral discrepancies and 285% worse drops under attacks that accuracy metrics miss.
-
PseudoBridge: Pseudo Code as the Bridge for Better Semantic and Logic Alignment in Code Retrieval
PseudoBridge uses LLM-synthesized pseudo-code to bridge NL semantics and PL logic plus logic-invariant style augmentation to boost robustness and generalization in code retrieval.
-
LEAF: Knowledge Distillation of Text Embedding Models with Teacher-Aligned Representations
LEAF distills teacher-aligned student embedding models that achieve new SOTA results on BEIR and MTEB for their size class while requiring only modest data and compute.
-
User eXperience Perception Insights Dataset (UXPID): Synthetic User Feedback from Public Industrial Forums
The paper introduces UXPID, a new dataset of 7130 LLM-annotated synthetic user feedback branches from industrial forums to support UX analysis and NLP tasks in software engineering.
-
Learning Adapter Rank via Symmetry Breaking
BayesLoRA applies diagonal rank-wise variational inference to break LoRA gauge symmetry and learn adapter rank with O(r) parameters.
-
CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models
CoT-VLA is a 7B VLA that generates future visual frames autoregressively as planning goals before actions, outperforming prior VLAs by 17% on real-world tasks and 6% in simulation.
-
Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
OpenVLA-OFT fine-tuning boosts LIBERO success rate from 76.5% to 97.1%, speeds action generation 26x, and outperforms baselines on real bimanual dexterous tasks.
-
DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control
DexVLA combines a scaled diffusion action expert with embodiment curriculum learning to achieve better generalization and performance than prior VLA models on diverse robot hardware and long-horizon tasks.
-
MiniMax-01: Scaling Foundation Models with Lightning Attention
MiniMax-01 models match GPT-4o and Claude-3.5-Sonnet performance while providing 20-32 times longer context windows through lightning attention and MoE scaling.
-
$\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
π₀ is a vision-language-action flow model trained on diverse multi-platform robot data that supports zero-shot task performance, language instruction following, and efficient fine-tuning for dexterous tasks.
-
GigaCheck: Detecting LLM-generated Content via Object-Centric Span Localization
GigaCheck detects LLM-generated text at both document and span levels by combining fine-tuned language-model embeddings with a DETR-like architecture that treats generated intervals as detectable objects.
-
Retrieval-Augmented Generation for Natural Language Processing: A Survey
The survey organizes RAG methods via a taxonomy of query-based, logits-based, latent, and parametric fusion with comparisons on accessibility, efficiency, applications, and challenges.
-
OpenVLA: An Open-Source Vision-Language-Action Model
OpenVLA achieves 16.5% higher task success than the 55B RT-2-X model across 29 tasks with 7x fewer parameters while enabling effective fine-tuning and quantization without performance loss.
-
DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
DROID is a new 76k-trajectory in-the-wild robot manipulation dataset spanning 564 scenes and 84 tasks that improves policy performance and generalization when used for training.
-
Chain-of-Verification Reduces Hallucination in Large Language Models
Chain-of-Verification reduces hallucinations in large language models by drafting responses, planning independent verification questions, answering them separately, and generating a final verified output.
-
MiniLLM: On-Policy Distillation of Large Language Models
MiniLLM distills large language models into smaller ones via reverse KL divergence and on-policy optimization, yielding higher-quality responses with lower exposure bias than standard KD baselines.
-
FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
FrugalGPT learns query-specific cascades across heterogeneous LLM APIs to match or exceed top-model accuracy at far lower cost.
-
R3M: A Universal Visual Representation for Robot Manipulation
A visual encoder pre-trained on diverse human videos with contrastive and language objectives improves simulated robot manipulation success by over 20% versus training from scratch and enables real Franka arm tasks from 20 demonstrations.
-
Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed
Denoising Student distills the multi-step denoising process of score-based and diffusion models into a single forward pass, matching GAN sampling speed while producing comparable sample quality on CIFAR-10, CelebA, and 256x256 LSUN.