ML News
new
|
past
|
best
|
rss
|
submit
about
121.
A Fix for Softmax and Cross-Entropy
(
arxiv.org
)
4 points
by
vpj
24 days ago
|
hide
|
past
|
pdf
|
discuss
122.
Min-P, Max Exaggeration: Critical Analysis of Min-P Sampling in Language Models
(
arxiv.org
)
1 point
by
wy35
24 days ago
|
hide
|
past
|
pdf
|
discuss
123.
Why is AI generated language so hard to understand?
(
arxiv.org
)
259 points
by
canjobear
24 days ago
|
hide
|
past
|
pdf
|
205 comments
124.
A Self-Defining Operator for Distributed Applications
(
arxiv.org
)
1 point
by
matt_d
24 days ago
|
hide
|
past
|
pdf
|
discuss
125.
Next-Concept Modeling: Fast, Parallel Coarse-to-Fine Text Generation
(
arxiv.org
)
2 points
by
ibobev
25 days ago
|
hide
|
past
|
pdf
|
discuss
126.
Benchmarking Multimodal Agents for Robot Use Across Diverse Tasks, Embodiments
(
arxiv.org
)
1 point
by
devy
25 days ago
|
hide
|
past
|
pdf
|
discuss
127.
LLM Multi-Agent Systems Are Vulnerable to Herding and Runaway Cascades
(
arxiv.org
)
1 point
by
ersinesen
25 days ago
|
hide
|
past
|
pdf
|
discuss
128.
MemoryTax: The Bitter Lesson of Agent Memory
(
arxiv.org
)
1 point
by
netsroht
25 days ago
|
hide
|
past
|
pdf
|
discuss
129.
Neural Computers
(
arxiv.org
)
2 points
by
oldfuture
25 days ago
|
hide
|
past
|
pdf
|
discuss
130.
The Psicology of an AI Hacker
(
arxiv.org
)
1 point
by
vmayoral
25 days ago
|
hide
|
past
|
pdf
|
1 comment
131.
Why is AI-generated language so hard to understand?
(
arxiv.org
)
4 points
by
Anon84
25 days ago
|
hide
|
past
|
pdf
|
discuss
132.
TorchTPU: Hybrid Eager/Compiled Architecture for Native PyTorch Execution on TPU
(
arxiv.org
)
1 point
by
matt_d
26 days ago
|
hide
|
past
|
pdf
|
1 comment
133.
Why is AI-generated language so hard to understand?
(
arxiv.org
)
4 points
by
ersinesen
26 days ago
|
hide
|
past
|
pdf
|
discuss
134.
Team of Gemini 4 Argon agents beats Minecraft
(
arxiv.org
)
2 points
by
taylorbuley
26 days ago
|
hide
|
past
|
pdf
|
discuss
135.
The alien space of science: Coherent but cognitively unavailable directions
(
arxiv.org
)
214 points
by
martincsweiss
26 days ago
|
hide
|
past
|
pdf
|
89 comments
136.
Every Time I Hire a Linguist, Inference Costs Go Down
(
arxiv.org
)
2 points
by
surprisetalk
26 days ago
|
hide
|
past
|
pdf
|
discuss
137.
Why are all LLMs Obsessed with Japanese Culture? [pdf]
(
arxiv.org
)
1 point
by
thinkingemote
26 days ago
|
hide
|
past
|
pdf
|
discuss
138.
Language models transmit behavioral traits via hidden signals in data
(
arxiv.org
)
2 points
by
convict
26 days ago
|
hide
|
past
|
pdf
|
discuss
139.
Compaction Laundering:Provenance Destruction in Context-Compacting Coding Agents
(
arxiv.org
)
2 points
by
ersinesen
26 days ago
|
hide
|
past
|
pdf
|
discuss
140.
How Much of a Harness Does a Strong Agent Need for Autonomous ML Engineering?
(
arxiv.org
)
2 points
by
brazukadev
27 days ago
|
hide
|
past
|
pdf
|
discuss
141.
XYEval: Agents say yes to bad advice
(
arxiv.org
)
2 points
by
xnx
27 days ago
|
hide
|
past
|
pdf
|
discuss
142.
CyberArena: Benchmarking AI Agents in Live Symmetric Attack-and-Defense Combat
(
arxiv.org
)
2 points
by
neutrinoliu
27 days ago
|
hide
|
past
|
pdf
|
discuss
143.
Forty Questions: Identifying a Language Model from One-Word Answers
(
arxiv.org
)
1 point
by
ersinesen
27 days ago
|
hide
|
past
|
pdf
|
discuss
144.
A team of Gemini 4 Argon agents beats Minecraft
(
arxiv.org
)
2 points
by
jonbaer
27 days ago
|
hide
|
past
|
pdf
|
discuss
145.
mini-Lean-Agent: A Coding-Agent Baseline for Lean
(
arxiv.org
)
2 points
by
matt_d
27 days ago
|
hide
|
past
|
pdf
|
discuss
146.
Diffeomorphic Optimization
(
arxiv.org
)
2 points
by
E-Reverance
28 days ago
|
hide
|
past
|
pdf
|
discuss
147.
Is Complexity an Illusion? (2024)
(
arxiv.org
)
4 points
by
the-mitr
28 days ago
|
hide
|
past
|
pdf
|
1 comment
148.
How Much of a Harness Does a Strong Agent Need for Autonomous ML Engineering?
(
arxiv.org
)
1 point
by
ibobev
28 days ago
|
hide
|
past
|
pdf
|
discuss
149.
Randomized test of an AI sales agent on 100 sites (ArXiv)
(
arxiv.org
)
1 point
by
benataiso
28 days ago
|
hide
|
past
|
pdf
|
discuss
150.
Gradient Routing Localizes and Removes Unintended Behaviors in RL
(
arxiv.org
)
1 point
by
andre15silva
28 days ago
|
hide
|
past
|
pdf
|
discuss
More
About
|
RSS
|
RSS (all)
|
HN arXiv