WeSearch
Hub / Tags / Distillation
TAG · #DISTILLATION

Distillation coverage.

Every story in the WeSearch catalog tagged with #distillation, chronological, with view counts. Subscribe to the per-tag RSS feed to follow this topic in your reader of choice.

21 stories tagged with #distillation, in publish-time order across the WeSearch catalog. Tag pages update as new stories ingest.

⌘ RSS feed for this tag →   or   search "Distillation"

RELATED TAGS
#ml4#ai4#self-distillation3#continual-learning1#reinforcement-learning1#idan-shenfeld1#mehul-damani1#jonas-h-botter1#pulkit-agrawal1#arxiv1#knowledge-distillation1#liquor1
HACKADAY

Distilling Stale Gasoline to Make it Usable Again

The propensity of gasoline to ‘go stale’ through the process of oxidation is the reason why gasoline that has been stored for a long period of time is considered to be unusable, as…

30 views ·
#gasoline#chemistry
TOMASZ TUNGUZ

Skill Distillation

How a personal AI agent built on markdown skills lets a frontier model teach smaller, local models to do real work, without retraining.…

14 views ·
#ai#productivity#technology
R/STABLEDIFFUSION

8-step FLUX.2-dev DMD2 distillation

22 views ·
DEV.TO (TOP)

How Model Distillation Actually Works (and What the 'China Distilled Our Model' Headlines Really Mean)

A practical, no-hype explainer of knowledge distillation in LLMs — the actual mechanics, why distilling from a closed API is different, and what the OpenAI/Anthropic vs DeepSeek al…

22 views ·
#ai#machinelearning#deeplearning
REASON MAGAZINE

High Liquor Taxes and a Home Distillation Ban Guarantee a Thriving Booze Black Market

Between a home distillation ban and high liquor taxes, government officials have created the perfect conditions for a black market in distilled spirits.…

22 views ·
#liquor#black market
ARXIV CS.AI

Counteraction-Aware Multi-Teacher On-Policy Distillation for General Capability Recovery with Domain Preservation

Domain specialization can improve LLM behavior in vertical domains, but often weakens the general capabilities inherited from the original model. Recent Multi-Teacher On-Policy Dis…

24 views ·
#artificial intelligence#machine learning#language models
ARXIV CS.AI

StepOPSD: Step-Aware Online Preference Distillation for Agent Reinforcement Learning

Reinforcement learning for multi-turn agents suffers from a credit-assignment mismatch: rewards are sparse and trajectory-level, while success often hinges on a few local decisions…

21 views ·
#artificial intelligence#reinforcement learning#machine learning
ARXIV CS.AI

When Does Adaptive Guidance Help? Belief-Aware Privileged Distillation for Autonomous Driving Under Partial Observability

Guided Soft Actor-Critic (GSAC) distills knowledge from a privileged full-state teacher to a partial-observation student for autonomous driving, but uses a fixed distillation coeff…

20 views ·
#robotics#artificial intelligence#machine learning
ARXIV CS.AI

PANDO: Efficient Multimodal AI Agents via Online Skill Distillation

Recent advances in multimodal web agents often rely on increased inference-time computation, including rollout search, verifier passes, offline skill discovery, and specialist mode…

15 views ·
#artificial intelligence#machine learning#technology
ARXIV CS.AI

EDGE-OPD: Internalizing Privileged Context with Evidence Guided On-Policy Distillation

On-Policy Distillation (OPD) has gained wide attraction as an LLM post-training paradigm due to its effectiveness in improving capabilities without introducing model distribution d…

13 views ·
#artificial intelligence#machine learning#research
ARXIV CS.AI

It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs

Contextual Integrity (CI) defines privacy not merely as keeping information hidden, but as governing information flows according to the norms of a given context. As large language …

16 views ·
#machine learning#artificial intelligence#privacy
ARXIV CS.AI

Consistently Informative Soft-Label Temperature for Knowledge Distillation

Knowledge distillation (KD) transfers knowledge from a high-capacity teacher to a compact student by matching their predictive distributions, with temperature scaling serving as a …

14 views ·
#machine learning#knowledge distillation#artificial intelligence
ARXIV CS.AI

AVSD: Adaptive-View Self-Distillation by Balancing Consensus and Teacher-Specific Privileged Signals

Self-distillation enables language models to learn on-policy from their own trajectories by using the same model as both student and teacher, with the teacher being conditioned on …

18 views ·
#machine learning#artificial intelligence#self-distillation
ARXIV CS.AI

PACD-Net: Pseudo-Augmented Contrastive Distillation for Glycemic Control Estimation from SMBG

Effective diabetes management requires continuous monitoring of glycemic levels. Clinically, glycemic control is assessed using metrics such as Time in Range (TIR), Time Below Rang…

16 views ·
#machine learning#artificial intelligence#healthcare
ARXIV CS.AI

What and When to Distill: Selective Hindsight Distillation for Multi-Turn Agents

Reinforcement learning can train LLM agents from sparse task rewards, but long-horizon credit assignment remains challenging: a single success-or-failure signal must be distributed…

16 views ·
#artificial intelligence#reinforcement learning#machine learning
ARXIV CS.AI

From Sparsity to Simplicity: Enabling Simpler Sequential Replacements via Sparse Attention Distillation

Self-attention serves as the core foundation of large-scale transformer pretraining, but its quadratic token interaction cost makes inference expensive. Replacing attention with si…

12 views ·
#machine learning#artificial intelligence#transformers
ARXIV CS.AI

SD-Search: On-Policy Hindsight Self-Distillation for Search-Augmented Reasoning

Search-augmented reasoning agents interleave internal reasoning with calls to an external retriever, and their performance relies on the quality of each issued query. However, unde…

13 views ·
#artificial intelligence#machine learning#information retrieval
ARXIV CS.AI

AMR-SD: Asymmetric Meta-Reflective Self-Distillation for Token-Level Credit Assignment

The alignment of Large Language Models (LLMs) for complex reasoning heavily relies on Reinforcement Learning with Verifiable Rewards (RLVR). However, standard algorithms like GRPO …

13 views ·
#artificial intelligence#machine learning#self-distillation
ARXIV CS.AI

DeltaPrompts: Escaping the Zero-Delta Trap in Multimodal Distillation

Distillation enables compact Vision-Language Models (VLMs) to obtain strong reasoning capabilities, yet the prompts driving this process are typically chosen via simple heuristics …

13 views ·
#machine learning#artificial intelligence#data science
ARXIV CS.AI

Towards Generalization of Block Attention via Automatic Segmentation and Block Distillation

Block attention, which processes the input as separate blocks that cannot attend to one another, offers significant potential to improve KV cache reuse in long-context scenarios su…

14 views ·
#artificial intelligence#machine learning#natural language processing
ARXIV.ORG

Self-Distillation Enables Continual Learning [PDF]

Continual learning, enabling models to acquire new skills and knowledge without degrading existing capabilities, remains a fundamental challenge for foundation models. While on-pol…

17 views ·
#machine learning#artificial intelligence#continual learning