Michael Kopp
@mkk20.bsky.social
43 followers
61 following
50 posts
Believer in memory to memory connections who wonders what "memory" and "compute" really mean.
Posts
Media
Videos
Starter Packs
Reposted by Michael Kopp
Michael Kopp
@mkk20.bsky.social
· Jun 12
HopaDIFF: Holistic-Partial Aware Fourier Conditioned Diffusion for Referring Human Action Segmentation in Multi-Person Scenarios
Action segmentation is a core challenge in high-level video understanding, aiming to partition untrimmed videos into segments and assign each a label from a predefined action set. Existing methods pri...
arxiv.org
Reposted by Michael Kopp
Reposted by Michael Kopp
Michael Kopp
@mkk20.bsky.social
· Jun 2
TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning
In-context learning, the ability of large language models to perform tasks using only examples provided in the prompt, has recently been adapted for time series forecasting. This paradigm enables zero...
arxiv.org
Reposted by Michael Kopp
Michael Kopp
@mkk20.bsky.social
· Jun 2
TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning
In-context learning, the ability of large language models to perform tasks using only examples provided in the prompt, has recently been adapted for time series forecasting. This paradigm enables zero...
arxiv.org
Michael Kopp
@mkk20.bsky.social
· Jun 2
TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning
In-context learning, the ability of large language models to perform tasks using only examples provided in the prompt, has recently been adapted for time series forecasting. This paradigm enables zero...
arxiv.org
Michael Kopp
@mkk20.bsky.social
· May 26
Classification of assembly tasks combining multiple primitive actions using Transformers and xLSTMs
The classification of human-performed assembly tasks is essential in collaborative robotics to ensure safety, anticipate robot actions, and facilitate robot learning. However, achieving reliable class...
arxiv.org
Michael Kopp
@mkk20.bsky.social
· May 24
xLSTM-SENet: xLSTM for Single-Channel Speech Enhancement
While attention-based architectures, such as Conformers, excel in speech enhancement, they face challenges such as scalability with respect to input sequence length. In contrast, the recently proposed...
arxiv.org
Michael Kopp
@mkk20.bsky.social
· May 21
The Guardian
@theguardian.com
· May 21
Most AI chatbots easily tricked into giving dangerous responses, study finds
Researchers say threat from ‘jailbroken’ chatbots trained to churn out illegal information is ‘tangible and concerning’
Hacked AI-powered chatbots threaten to make dangerous knowledge readily available by churning out illicit information the programs absorb during training, researchers say.
The warning comes amid a disturbing trend for chatbots that have been “jailbroken” to circumvent their built-in safety controls. The restrictions are supposed to prevent the programs from providing harmful, biased or inappropriate responses to users’ questions. Continue reading...
www.theguardian.com
Michael Kopp
@mkk20.bsky.social
· Apr 15
TechCrunch
@techcrunch.com
· Apr 15
OpenAI is reportedly developing its own X-like social media platform
OpenAI is building its own X-like social media network, according to a new report from The Verge. The project is still in the early stages, but there’s an internal prototype focused on ChatGPT’s image generation that contains a social feed. The report states that it’s unknown if OpenAI plans to launch the social network as a […]
tcrn.ch
Michael Kopp
@mkk20.bsky.social
· Apr 15
Michael Kopp
@mkk20.bsky.social
· Apr 13
David Marx
@digthatdata.bsky.social
· Apr 13
Position: The Platonic Representation Hypothesis
We argue that representations in AI models, particularly deep networks, are converging. First, we survey many examples of convergence in the literature: over time and across multiple domains, the w...
proceedings.mlr.press
Michael Kopp
@mkk20.bsky.social
· Apr 13
Cat, Rat, Meow: On the Alignment of Language Model and Human Term-Similarity Judgments
Small and mid-sized generative language models have gained increasing attention. Their size and availability make them amenable to being analyzed at a behavioral as well as a representational level, a...
arxiv.org
Michael Kopp
@mkk20.bsky.social
· Apr 6
Michael Kopp
@mkk20.bsky.social
· Apr 6
Zero-Shot Reinforcement Learning via Function Encoders
Although reinforcement learning (RL) can solve many challenging sequential decision making problems, achieving zero-shot transfer across related tasks remains a challenge. The difficulty lies in findi...
arxiv.org
Michael Kopp
@mkk20.bsky.social
· Apr 3
Thomas Seal
@twseal.bsky.social
· Apr 3
This Is the Formula Trump's Team Used to Calculate Tariffs
President Donald Trump’s administration calculated its raft of new tariffs primarily based on existing trade balances — a departure from pledges to match the tariff rates and other trade barriers from...
www.bloomberg.com
Michael Kopp
@mkk20.bsky.social
· Mar 29
Michael Kopp
@mkk20.bsky.social
· Mar 29
Michael Kopp
@mkk20.bsky.social
· Mar 29