AI Research

Feeds to Scour
SubscribedAll
Scoured 245 posts in 7.6 ms

ABC-Bench: An Agentic Bio-Capabilities Benchmark for Biosecurity

馃敁Open Source AIContent type: Academic
arxiv.orgHacker News

Validity Threats for Foundation Model Research

鈿欙笍ML EngineeringContent type: Academic
arxiv.org

Dynamic Linear Attention

馃aiContent type: Academic
arxiv.org

Cutting LLM Evaluation Costs with SySRs: A Bandit Algorithm that Provably Exploits Model Similarity

馃挰LLMsContent type: Academic
arxiv.org

Mitigating Manifold Departure: Uncertainty-Aware Subspace Rectification for Trustworthy MLLM Decoding

馃挰LLMsContent type: Academic
arxiv.org

Depth over Fidelity in Fixed-Budget Noisy Evolution Strategies

鈿欙笍ML EngineeringContent type: Academic
arxiv.org

Deliberate Evolution: Agentic Reasoning for Sample-Efficient Symbolic Regression with LLMs

馃挰LLMsContent type: Academic
arxiv.org

When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models

馃攼AI SafetyContent type: Academic
arxiv.org

Shared Semantics, Divergent Mechanisms: Unsupervised Feature Discovery by Aligning Semantics and Mechanisms

馃攼AI SafetyContent type: Academic
arxiv.org

Efficiently Learning Drifting Halfspaces with Massart Noise

鈿欙笍ML EngineeringContent type: Academic
arxiv.org

Semantic Constraint Synthesis for Adaptive Trajectory Optimization via Large Language Models

馃攼AI SafetyContent type: Academic
arxiv.org

A Universal Dense Football Event Representation Based on TabTransformer

馃挰LLMsContent type: Academic
arxiv.org

Mix, Don't Pick: Why Synthetic Corpus Composition Matters for Time Series Foundation Model Pretraining

馃搱Time SeriesContent type: Academic
arxiv.org

DyCon: Dynamic Reasoning Control via Evolving Difficulty Modeling

馃aiContent type: Academic
arxiv.org

UniSVQ: 2-bit Unified Scalar-Vector Quantization

鈿欙笍ML EngineeringContent type: Academic
arxiv.org

Plug-and-Play Guidance for Discrete Diffusion Models via Gradient-Informed Logit Correction

馃aiContent type: Academic
arxiv.org

Memetic Capture: A Pluralistic Policy Framework for Governing AI-Driven Cultural Disempowerment

馃aiContent type: Academic
arxiv.org

From Observation to Intervention: A Causal Audit of Expert Importance in Mixture-of-Experts Models

鈿欙笍ML EngineeringContent type: Academic
arxiv.org

Generative Modeling of Discrete Latent Structures via Dynamic Policy Gradients

馃挰LLMsContent type: Academic
arxiv.org

AnyMod-LLVE: Low-Light Video Enhancement with Modality-Agnostic Inference

馃敁Open Source AIContent 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