ML News
new
|
past
|
best
|
rss
|
submit
about
1.
Self-Improvement Memory Enables Continual Recursive Self-Improvement
(
arxiv.org
)
4 points
by
omarsar
7 hours ago
|
hide
|
past
|
pdf
|
1 comment
2.
Anatomy of an Agent Harness: 30 decisions, invariants and corner cases
(
arxiv.org
)
6 points
by
reshamjoshi_
23 hours ago
|
hide
|
past
|
pdf
|
discuss
3.
Evolving Infra: Agent-Adaptive LLM Serving at Scale
(
arxiv.org
)
1 point
by
matt_d
1 day ago
|
hide
|
past
|
pdf
|
discuss
4.
Benchmarking Coding Agents Under Evolving Requirements
(
arxiv.org
)
5 points
by
DeathArrow
1 day ago
|
hide
|
past
|
pdf
|
discuss
5.
Browser Immune System (BIS) Innate and Adaptive Threat Detection in the Browser
(
arxiv.org
)
2 points
by
eduardoworrel
1 day ago
|
hide
|
past
|
pdf
|
discuss
6.
HCCL: Collective Communication for Meta Training and Inference Accelerators
(
arxiv.org
)
1 point
by
ingve
1 day ago
|
hide
|
past
|
pdf
|
discuss
7.
No Second Run: Does RSI Stop at Frontier Pre-Training?
(
arxiv.org
)
1 point
by
theanonymousone
2 days ago
|
hide
|
past
|
pdf
|
discuss
8.
Flattening Every Memory Peak in Long-Context Mixture-of-Experts Training
(
arxiv.org
)
3 points
by
gmays
2 days ago
|
hide
|
past
|
pdf
|
discuss
9.
Tensor Seeks Layout: Formalizing Layout Selection for ML Compilers
(
arxiv.org
)
1 point
by
matt_d
3 days ago
|
hide
|
past
|
pdf
|
discuss
10.
Leaderboard Hacking: Preference-Based Model Evals Vulnerable to Manipulation
(
arxiv.org
)
1 point
by
Betelbuddy
3 days ago
|
hide
|
past
|
pdf
|
discuss
11.
Use LLM for direct robot control
(
arxiv.org
)
1 point
by
kevinlu
3 days ago
|
hide
|
past
|
pdf
|
1 comment
12.
SlopCodeBench: Benchmarking How Coding Agents Degrade over Long-Horizon Tasks
(
arxiv.org
)
3 points
by
zdw
3 days ago
|
hide
|
past
|
pdf
|
discuss
13.
The Curse of Recursion: Training on Generated Data Makes Models Forget (2024)
(
arxiv.org
)
2 points
by
Eridanus2
3 days ago
|
hide
|
past
|
pdf
|
1 comment
14.
MLIRBench – A Benchmark and Dataset for Compiler and Hardware-Aware Reasoning
(
arxiv.org
)
2 points
by
matt_d
4 days ago
|
hide
|
past
|
pdf
|
discuss
15.
ShadowPrefill: Keeping Your Next Model Warm for Model Routing in Agentic Serving
(
arxiv.org
)
2 points
by
matt_d
4 days ago
|
hide
|
past
|
pdf
|
discuss
16.
Xeno-Interpretability: Investigating the Alien Minds of LLMs
(
arxiv.org
)
1 point
by
droidjj
5 days ago
|
hide
|
past
|
pdf
|
discuss
17.
Air-LLM: Broadcasting AI Weights for Edge LLM Inference via RF Computing
(
arxiv.org
)
1 point
by
nolist_policy
5 days ago
|
hide
|
past
|
pdf
|
discuss
18.
Remote Labor Index: Measuring AI Automation of Remote Work
(
arxiv.org
)
2 points
by
doener
5 days ago
|
hide
|
past
|
pdf
|
1 comment
19.
DIMWIT: Directly Invoking Models Without Intensive Tuning
(
arxiv.org
)
2 points
by
matt_d
6 days ago
|
hide
|
past
|
pdf
|
discuss
20.
Are Dense Rewards Worth Their Tokens in GRPO?
(
arxiv.org
)
1 point
by
vikashjohn2505
6 days ago
|
hide
|
past
|
pdf
|
1 comment
21.
E-means: outperforming k-means (in one-tenth the epochs)
(
arxiv.org
)
2 points
by
Anon84
7 days ago
|
hide
|
past
|
pdf
|
discuss
22.
The Memory Trap: Language Agents Overgeneralize from Benign Interactions
(
arxiv.org
)
1 point
by
matt_d
7 days ago
|
hide
|
past
|
pdf
|
discuss
23.
The Surprising Effectiveness of Deleting Weights in LLM Post-Training
(
arxiv.org
)
30 points
by
theanonymousone
7 days ago
|
hide
|
past
|
pdf
|
discuss
24.
Doc2Harness: Benchmarking how well AI builds agent harnesses
(
arxiv.org
)
2 points
by
waximabbax
7 days ago
|
hide
|
past
|
pdf
|
discuss
25.
AutoCompress: Automated Hardware-Guided Model Compression
(
arxiv.org
)
2 points
by
gmays
7 days ago
|
hide
|
past
|
pdf
|
discuss
26.
WikiSkill: Compiling Agent Experience into Knowledge for Skill Evolution
(
arxiv.org
)
1 point
by
gmays
7 days ago
|
hide
|
past
|
pdf
|
discuss
27.
MemoryDojo: Benchmarking Poisoning Through LLM Agent Memory
(
arxiv.org
)
1 point
by
anatolii1309
7 days ago
|
hide
|
past
|
pdf
|
discuss
28.
Recursive Self-Improving Terminal Agents via Recursive Self-Rewrite
(
arxiv.org
)
2 points
by
UncleOxidant
8 days ago
|
hide
|
past
|
pdf
|
discuss
29.
I Think, Therefore I Attack
(
arxiv.org
)
2 points
by
gok
8 days ago
|
hide
|
past
|
pdf
|
discuss
30.
Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators
(
arxiv.org
)
2 points
by
matt_d
8 days ago
|
hide
|
past
|
pdf
|
discuss
More
About
|
RSS
|
RSS (all)
|
HN arXiv