ML Research

Feeds to Scour
SubscribedAll
Scoured 192 posts in 6.7 ms

Generative Modeling of Discrete Latent Structures via Dynamic Policy Gradients

 📚CS Research  Content type: Academic
arxiv.org·

Two-Layer Linear Auto-Regressive Models Estimate Latent States

 📚CS Research  Content type: Academic
arxiv.org·
Less-relevant results

KaiFelixBennett/gemma4-turboquant-rdna4: Run Gemma-4-31B at full 256K context on a $1,400 AMD RDNA4 GPU (gfx1201): TurboQuant KV cache + HIP-graph-safe Flash-Attention for llama.cpp, fully measured on real hardware.

 🤖AI  Content type: Code
github.com··Hacker News

Fourier Features Let Agents Learn High Precision Policies with Imitation Learning

 📚CS Research  Content type: Academic
arxiv.org·

SHAPO: Sharpness-Aware Policy Optimization for Safe Exploration

 🎮Reinforcement Learning  Content type: Academic
arxiv.org·

Once-for-All: Scalable Simultaneous Forecasting via Equilibrium State Estimation

 📚CS Research  Content type: Academic
arxiv.org·

Textual Supervision Enhances Geospatial Representations in Vision-Language Models

 📚CS Research  Content type: Academic
arxiv.org·

ECA: Efficient Continual Alignment for Open-Ended Image-to-Text Generation

 📚CS Research  Content type: Academic
arxiv.org·

ERAlign: Energy-based Representation Alignment of GNNs and LLMs on Text-attributed Graphs

 Generative AI  Content type: Academic
arxiv.org·

Neuron-based Personality Trait Induction in Large Language Models

 🧠LLMs  Content type: Academic
arxiv.org·

Gated DeltaNet, From First Principles

 🧠LLMs  Content type: Blog
sankalp.bearblog.dev·

Viral Proteins Reveal Geometry of Protein Language Models

 📚CS Research  Content type: Academic
arxiv.org·

Flexible Kernels for Protein Property Prediction

 📚CS Research  Content type: Academic
arxiv.org·

MLUBench: A Benchmark for Lifelong Unlearning Evaluation in MLLMs

 📚CS Research  Content type: Academic
arxiv.org·

Evaluation of ML Resource Utilization Requires Model Life Cycle Assessment

 📚CS Research  Content type: Academic
arxiv.org·

PolyFlow: Safe and Efficient Polytope-Constrained Flow Matching with Constraint Embedding and Projection-free Update

 📚CS Research  Content type: Academic
arxiv.org·

Zero-source LLM Hallucination Detection with Human-like Criteria Probing

 📚CS Research  Content type: Academic
arxiv.org·

How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs

 🎮Reinforcement Learning  Content type: Academic

Selecting Samples on Graphs: A Unified Dataset Pruning Framework for Lossless Training Acceleration

 📚CS Research  Content type: Academic
arxiv.org·

Counterfactual Transport Flows for Offline Conservative Trajectory Refinement

 📚CS Research  Content type: Academic
arxiv.org·
Sign up or log in to see more results

Keyboard Shortcuts

Navigation

Next / previous item
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help