AllLLMRoboticsStartupsResearchEthicsBusinessHardwareAutonomousMedicineCreative
Topic

#LLM

Curated coverage on «LLM»: releases, research, benchmarks, open-source.

4839 articles-77% vs prev. week324 this week
Subscribe
RELATED:#Business#Hardware#Research#Creative#Startups#Ethics#Autonomous#Robotics#Medicine
Distilled Diffusion Models Learn to Forget Unwanted Concepts via DPO
LLM·arXiv cs.CV

Distilled Diffusion Models Learn to Forget Unwanted Concepts via DPO

Oct 9, 2026·2 min
SPLIT-RL Teaches VLMs to See and Reason Separately: +1.4–6.1 pp Over GRPO
LLM

SPLIT-RL Teaches VLMs to See and Reason Separately: +1.4–6.1 pp Over GRPO

Oct 9, 2026·2 min
Flow matching: velocity scaling cuts FID from 28.0 to 12.2 on ImageNet-256
LLM

Flow matching: velocity scaling cuts FID from 28.0 to 12.2 on ImageNet-256

Oct 9, 2026·2 min
VICO Trains VLMs on Rewritable Images: Up to +5.0% on New Tasks
LLM

VICO Trains VLMs on Rewritable Images: Up to +5.0% on New Tasks

Oct 9, 2026·2 min
DOGS Beats 9 Baseline Methods at Logo Generation Across Two Renderers
LLM·arXiv cs.CV

DOGS Beats 9 Baseline Methods at Logo Generation Across Two Renderers

DOGS drops prompt rewriting: a GFlowNet samples a logo design graph and penalizes similarity to existing marks. The authors compared it with nine baseline methods.

Oct 9, 2026·2 min
LinSlot Teaches a Neural Network to Break a Scene Into Objects and Their Attributes Without Labels
LLM·arXiv cs.CV

LinSlot Teaches a Neural Network to Break a Scene Into Objects and Their Attributes Without Labels

The new LinSlot architecture finds objects and their attributes in images without labels, building on the linear representation hypothesis. The authors claim DCI…

Oct 9, 2026·2 min
OcuFlow Removes Eyeglass Glare in One Step and Wins 67.32% of Votes in a Blind Test
LLM·arXiv cs.CV

OcuFlow Removes Eyeglass Glare in One Step and Wins 67.32% of Votes in a Blind Test

The OcuFlow authors built OcuBench, a benchmark of 11 470 images, and trained a model that removes eyeglass glare in a single step. In a blind survey it beat its…

Oct 9, 2026·3 min
Researchers release VR180 dataset shot on Blackmagic cameras: 1211 stereo samples
LLM·arXiv cs.CV

Researchers release VR180 dataset shot on Blackmagic cameras: 1211 stereo samples

First VR180 dataset captured directly on Blackmagic URSA Cine Immersive: 636 videos, 575 photos, factory calibration, and a finding that fisheye needs 38% more…

Oct 9, 2026·2 min
Top themes
01SLVR Adds 14.2 Points on BLINK Relation to Qwen2.5-VL-7B Without Text CoTOct 9, 2026·2 min02Google Releases a Workplace AI Agent for Enterprises, but Pricing and Integrations Remain Open QuestionsOct 9, 2026·2 min03Researchers Prove Why Adversarial Training Makes Saliency Maps SparseOct 9, 2026·2 min04Subliminal learning passed a backdoor through numbers: 23.5% of replies in FrenchOct 9, 2026·2 min05PXtal Beats Baseline Models on Six Benchmarks, Four of Them Zero-ShotOct 9, 2026·2 min
Nullify Erases Knowledge From LLMs Without Retraining, Using Null-Space Vectors
LLM·arXiv cs.LG

Nullify Erases Knowledge From LLMs Without Retraining, Using Null-Space Vectors

Oct 9, 2026·2 min
CARing teaches LLMs to predict diagnoses: R@30 hits 46.52% on MIMIC-IV
LLM·arXiv cs.LG

CARing teaches LLMs to predict diagnoses: R@30 hits 46.52% on MIMIC-IV

Oct 9, 2026·2 min
Visible CoT Does Not Universally Improve SQL and pandas Code Generation, New Study Finds
LLM·arXiv cs.LG

Visible CoT Does Not Universally Improve SQL and pandas Code Generation, New Study Finds

Oct 9, 2026·2 min
D-SLR Replaces Truncated SVD With Three Decompositions and No Tuning
LLM·arXiv cs.LG

D-SLR Replaces Truncated SVD With Three Decompositions and No Tuning

Oct 9, 2026·2 min
Phase-HDC trains a model with no optimizer history and stores 16–23x less than Adam
LLM·arXiv cs.LG

Phase-HDC trains a model with no optimizer history and stores 16–23x less than Adam

Phase-HDC replaces Adam's moments with a threshold on the current gradient and stores 16–23x less than float32 Adam. The cost: about five points of accuracy on…

Oct 9, 2026·3 min
IKNO for Navier–Stokes Stays Accurate Under Rotation, With 5.6x Fewer Parameters Than TFN
LLM·arXiv cs.LG

IKNO for Navier–Stokes Stays Accurate Under Rotation, With 5.6x Fewer Parameters Than TFN

Researchers propose IKNO, a compact graph model whose predictions strictly follow coordinate rotations in 3D flows. It matches TFN accuracy with 5.6× fewer…

Oct 9, 2026·2 min
LoopOPD Teaches Looped Language Models to Improve Through Their Own Loops
LLM·arXiv cs.LG

LoopOPD Teaches Looped Language Models to Improve Through Their Own Loops

LoopOPD makes an intermediate loop of a LoopLM learn from the final loop of the same model, with no external teacher. Tested on Ouro-Thinking, trained on math only.

Oct 9, 2026·2 min
MoE Router Telemetry Leaks Fine-Tuning Data: Attack Gains 2.7–9.4 pp in Accuracy
LLM·arXiv cs.LG

MoE Router Telemetry Leaks Fine-Tuning Data: Attack Gains 2.7–9.4 pp in Accuracy

Oct 9, 2026·3 min
80 Synthetic Dialogues Are Enough to Train Activation Probes for Gemma-3-27B, but Not Everywhere
LLM·arXiv cs.LG

80 Synthetic Dialogues Are Enough to Train Activation Probes for Gemma-3-27B, but Not Everywhere

Oct 9, 2026·2 min
Temporal Transformer for the CAN Bus Catches Anomalies Without Sharing Raw Data
LLM·arXiv cs.LG

Temporal Transformer for the CAN Bus Catches Anomalies Without Sharing Raw Data

Oct 9, 2026·2 min
Freezing the Decoder in KV-Cache Compression Saves 3x Memory but Doesn't Improve Accuracy
LLM·arXiv cs.LG

Freezing the Decoder in KV-Cache Compression Saves 3x Memory but Doesn't Improve Accuracy

Oct 9, 2026·2 min
SFT-as-Context Restores General Skills in Fine-Tuned LLMs, Within 2.2 Points
LLM·arXiv cs.CL

SFT-as-Context Restores General Skills in Fine-Tuned LLMs, Within 2.2 Points

Oct 9, 2026·3 min
Lapras replaces CoT with latent reasoning: up to +10.79% F1 with 23.9x fewer tokens
LLM

Lapras replaces CoT with latent reasoning: up to +10.79% F1 with 23.9x fewer tokens

Oct 9, 2026·2 min
Doctors Don't Ask LLMs About Diagnoses: 127 833 Queries vs. 58 Benchmarks
LLM

Doctors Don't Ask LLMs About Diagnoses: 127 833 Queries vs. 58 Benchmarks

Oct 9, 2026·2 min
FedAlphaEdit Merges Knowledge Edits from Different Organizations into One LLM Without Sharing Data
LLM

FedAlphaEdit Merges Knowledge Edits from Different Organizations into One LLM Without Sharing Data

Oct 9, 2026·2 min
Three LLMs Follow Prompts for Stutters and Interruptions Poorly; Rules Do Better
LLM·arXiv cs.CL

Three LLMs Follow Prompts for Stutters and Interruptions Poorly; Rules Do Better

The tau-Voice authors tested how three LLMs imitate disfluencies, interruptions and backchanneling in user simulators. A deterministic algorithm proved more…

Oct 9, 2026·2 min
Sociolinguistics Instead of LLM Judges: Testing User-Simulator Personas on 5 Agents
LLM·arXiv cs.CL

Sociolinguistics Instead of LLM Judges: Testing User-Simulator Personas on 5 Agents

A pilot arXiv study defines simulator personas through measurable style parameters and checks them with stylometry on five customer-service agents.

Oct 9, 2026·2 min
Related topics
Business 1160Research 499Robotics 178Hardware 101Autonomous 17Startups 9Medicine 8Ethics 5