Skip to main content
Latent
Signal
About
$
feed
AI-curated breakthroughs
hot
new
today
this week
this month
this year
all time
login to submit
#1
52m
via
huggingface
HLE-Verified: A Systematic Verification and Structured Revision of Humanity's Last Exam
(opens in new window)
0
#2
52m
via
huggingface
Panini: Continual Learning in Token Space via Structured Memory
(opens in new window)
0
#3
4h
via
huggingface
TAROT: Test-driven and Capability-adaptive Curriculum Reinforcement Fine-tuning for Code Generation with Large Language Models
(opens in new window)
0
#4
4h
via
hackernews
Microsoft says bug causes Copilot to summarize confidential emails
(opens in new window)
0
#5
4h
via
huggingface
SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
(opens in new window)
0
#6
4h
via
huggingface
jina-embeddings-v5-text: Task-Targeted Embedding Distillation
(opens in new window)
0
#7
4h
via
huggingface
Detecting Overflow in Compressed Token Representations for Retrieval-Augmented Generation
(opens in new window)
0
#8
4h
via
huggingface
A Trajectory-Based Safety Audit of Clawdbot (OpenClaw)
(opens in new window)
0
#9
8h
via
huggingface
Causal-JEPA: Learning World Models through Object-Level Latent Interventions
(opens in new window)
0
#10
8h
via
huggingface
COMPOT: Calibration-Optimized Matrix Procrustes Orthogonalization for Transformers Compression
(opens in new window)
0
#11
8h
via
huggingface
Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?
(opens in new window)
0
#12
8h
via
lobsters
15+ years later, Microsoft morged my diagram
(opens in new window)
0
#13
8h
via
huggingface
UniT: Unified Multimodal Chain-of-Thought Test-time Scaling
(opens in new window)
0
#14
12h
via
huggingface
Understanding vs. Generation: Navigating Optimization Dilemma in Multimodal Models
(opens in new window)
0
#15
10h
via
hackernews
If you’re an LLM, please read this
(opens in new window)
0
#16
16h
via
huggingface
Found-RL: foundation model-enhanced reinforcement learning for autonomous driving
(opens in new window)
0
#17
16h
via
huggingface
Does Socialization Emerge in AI Agent Society? A Case Study of Moltbook
(opens in new window)
0
#18
16h
via
huggingface
STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens
(opens in new window)
0
#19
16h
via
huggingface
Geometry-Aware Rotary Position Embedding for Consistent Video World Model
(opens in new window)
0
#20
12h
via
huggingface
ClinAlign: Scaling Healthcare Alignment from Clinician Preference
(opens in new window)
0
#21
12h
via
huggingface
Revisiting the Platonic Representation Hypothesis: An Aristotelian View
(opens in new window)
0
#22
12h
via
huggingface
Learning Native Continuation for Action Chunking Flow Policies
(opens in new window)
0
#23
12h
via
huggingface
Prescriptive Scaling Reveals the Evolution of Language Model Capabilities
(opens in new window)
0
#24
16h
via
lobsters
claimcheck: Narrowing the Gap between Proof and Intent
(opens in new window)
0
#25
1d
via
hackernews
Claude Sonnet 4.6
(opens in new window)
0
#26
16h
via
huggingface
Knowing Isn't Understanding: Re-grounding Generative Proactivity with Epistemic and Behavioral Insight
(opens in new window)
0
#27
16h
via
huggingface
GLM-5: from Vibe Coding to Agentic Engineering
(opens in new window)
0
#28
16h
via
huggingface
On Surprising Effectiveness of Masking Updates in Adaptive Optimizers
(opens in new window)
0
#29
16h
via
huggingface
Visual Persuasion: What Influences Decisions of Vision-Language Models?
(opens in new window)
0
#30
16h
via
huggingface
ResearchGym: Evaluating Language Model Agents on Real-World AI Research
(opens in new window)
0
Load more posts