Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

We’re excited to introduce KAME: Tandem Architecture for Enhancing Knowledge in Real-Time Speech-to-Speech Conversational AI, accepted at #ICASSP2026! 🐢 Blog Paper Can a speech AI think deeply without pausing to process? In real conversation, we don’t wait until we’ve fully worked out what we want to say—we start talking,... and our thoughts catch up as the sentence unfolds. Fast speech-to-speech models achieve this, but their reasoning tends to stay shallow. Cascaded pipelines that route through a knowledgeable LLM are smarter, but the added latency breaks the flow—they fall back to "think, then speak." In our new paper, we propose a way to break this trade-off. We call it KAME (Turtle in Japanese). A speech-to-speech model handles the fast response loop and starts replying immediately. In parallel, a backend LLM runs asynchronously, generating response candidates that are continuously injected as "oracle" signals in real time. This shifts the AI paradigm from "think, then speak" to "speak while thinking." The backend LLM is completely swappable. You can plug in GPT-4.1, Claude Opus, or Gemini 2.5 Flash depending on the task without changing the frontend. In our experiments, Claude tended to score higher on reasoning, while GPT did better on humanities questions. Try the model yourself here:show more

Sakana AI

138,723 subscribers

293,975 Aufrufe • vor 4 Monaten •via X (Twitter)

Bildung Wissenschaft & Technologie #ICASSP2026

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Speech-native models like Moshi sound great and answer fast, but aren’t as smart as text LLMs. In our new paper, MoshiRAG, we show how Moshi can ask for advice from a text LLM or a knowledge base. The tricky part is how to do this in real time without adding latency. 🧵

Speech-native models like Moshi sound great and answer fast, but aren’t as smart as text LLMs. In our new paper, MoshiRAG, we show how Moshi can ask for advice from a text LLM or a knowledge base. The tricky part is how to do this in real time without adding latency. 🧵

kyutai

53,142 Aufrufe • vor 4 Monaten

Mati Staniszewski on why ElevenLabs is betting on a cascaded approach for voice agents: “Our approach, as you think about voice agents, conversational agents, is effectively a cascaded approach. You use transcription or speech-to-text, an LLM, text-to-speech, and orchestrate all of that together. Then you have speech-to-speech, which goes directly from speech, and there’s a speech response on the other side. Today, we are optimizing heavily on a cascaded approach. As we work with a lot of the businesses and enterprises, they will need that visibility into what happens. They will want to execute certain tasks on top of that. They want good visibility into each of the steps and great accuracy of all the models. But beyond that, they can abstract away what’s the LLM layer, what’s the intelligence layer, and the integrations are easier in that system. That’s where we are betting a lot of the research work on how you can make that great, and we think we can make that great.” John Collison @matiii ElevenLabs

Mati Staniszewski on why ElevenLabs is betting on a cascaded approach for voice agents: “Our approach, as you think about voice agents, conversational agents, is effectively a cascaded approach. You use transcription or speech-to-text, an LLM, text-to-speech, and orchestrate all of that together. Then you have speech-to-speech, which goes directly from speech, and there’s a speech response on the other side. Today, we are optimizing heavily on a cascaded approach. As we work with a lot of the businesses and enterprises, they will need that visibility into what happens. They will want to execute certain tasks on top of that. They want good visibility into each of the steps and great accuracy of all the models. But beyond that, they can abstract away what’s the LLM layer, what’s the intelligence layer, and the integrations are easier in that system. That’s where we are betting a lot of the research work on how you can make that great, and we think we can make that great.” John Collison @matiii ElevenLabs

Stripe

18,535 Aufrufe • vor 4 Monaten

OpenAI shipped a new speech-to-speech model today: gpt-realtime-2 This is the first speech-to-speech model good enough to use in my voice agents that do "real work." Or real play, for that matter. Here's gpt-realtime-2 as the brain of the ship AI in Gradient Bang. The voice-to-voice response and tool calling times here are unedited, so you can see exactly what the interaction with the model is like in an agent with a very complex system instruction and frequent tool calls. (I did clip out the subagent task execution segments, after gpt-realtime-2 starts a subagent via a tool call. Subagents in this config used gpt-5.2 "medium" effort.)

OpenAI shipped a new speech-to-speech model today: gpt-realtime-2 This is the first speech-to-speech model good enough to use in my voice agents that do "real work." Or real play, for that matter. Here's gpt-realtime-2 as the brain of the ship AI in Gradient Bang. The voice-to-voice response and tool calling times here are unedited, so you can see exactly what the interaction with the model is like in an agent with a very complex system instruction and frequent tool calls. (I did clip out the subagent task execution segments, after gpt-realtime-2 starts a subagent via a tool call. Subagents in this config used gpt-5.2 "medium" effort.)

kwindla

55,222 Aufrufe • vor 3 Monaten

Pocket TTS goes multilingual! Now you can use our 100M-parameter models to generate speech in six languages, fast enough to run real-time without a GPU. We also improved the quality of the English model while keeping the same size. And all of this is open-source.

Pocket TTS goes multilingual! Now you can use our 100M-parameter models to generate speech in six languages, fast enough to run real-time without a GPU. We also improved the quality of the English model while keeping the same size. And all of this is open-source.

kyutai

29,702 Aufrufe • vor 4 Monaten

This is the fastest text-to-speech and speech-to-text API out there. It's under 250 ms to first-byte latency. That's what we need to deploy conversational AI applications everywhere! (I can't wait for the death of automated voice machines.) Look at the attached video. For the first time, I could have a conversation with an AI agent in real time without awkward pauses. This technology is Aura from Deepgram. It's the fastest text-to-speech option I've seen. Here is a GitHub repository with the demo in the video: You can use it to build a conversational AI application using natural voice. You'll need a Deepgram API Key and an OpenAI API Key. Thanks to Deepgram for giving me access to Aura and collaborating with me on this post. If you want to learn more about Aura, here is the announcement post:

This is the fastest text-to-speech and speech-to-text API out there. It's under 250 ms to first-byte latency. That's what we need to deploy conversational AI applications everywhere! (I can't wait for the death of automated voice machines.) Look at the attached video. For the first time, I could have a conversation with an AI agent in real time without awkward pauses. This technology is Aura from Deepgram. It's the fastest text-to-speech option I've seen. Here is a GitHub repository with the demo in the video: You can use it to build a conversational AI application using natural voice. You'll need a Deepgram API Key and an OpenAI API Key. Thanks to Deepgram for giving me access to Aura and collaborating with me on this post. If you want to learn more about Aura, here is the announcement post:

Santiago

185,640 Aufrufe • vor 2 Jahren

Google presents AudioPaLM: A Large Language Model That Can Speak and Listen paper page: introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models, PaLM-2 [Anil et al., 2023] and AudioLM [Borsos et al., 2022], into a unified multimodal architecture that can process and generate text and speech with applications including speech recognition and speech-to-speech translation. AudioPaLM inherits the capability to preserve paralinguistic information such as speaker identity and intonation from AudioLM and the linguistic knowledge present only in text large language models such as PaLM-2. We demonstrate that initializing AudioPaLM with the weights of a text-only large language model improves speech processing, successfully leveraging the larger quantity of text training data used in pretraining to assist with the speech tasks. The resulting model significantly outperforms existing systems for speech translation tasks and has the ability to perform zero-shot speech-to-text translation for many languages for which input/target language combinations were not seen in training. AudioPaLM also demonstrates features of audio language models, such as transferring a voice across languages based on a short spoken prompt.

Google presents AudioPaLM: A Large Language Model That Can Speak and Listen paper page: introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models, PaLM-2 [Anil et al., 2023] and AudioLM [Borsos et al., 2022], into a unified multimodal architecture that can process and generate text and speech with applications including speech recognition and speech-to-speech translation. AudioPaLM inherits the capability to preserve paralinguistic information such as speaker identity and intonation from AudioLM and the linguistic knowledge present only in text large language models such as PaLM-2. We demonstrate that initializing AudioPaLM with the weights of a text-only large language model improves speech processing, successfully leveraging the larger quantity of text training data used in pretraining to assist with the speech tasks. The resulting model significantly outperforms existing systems for speech translation tasks and has the ability to perform zero-shot speech-to-text translation for many languages for which input/target language combinations were not seen in training. AudioPaLM also demonstrates features of audio language models, such as transferring a voice across languages based on a short spoken prompt.

AK

290,517 Aufrufe • vor 3 Jahren

Today, we released Gemini 3.5 Live Translate, our latest audio model for live speech-to-speech translation. It supports over 70 languages and starts translating as soon as you start talking, streaming translations while listening to what you say next. No awkward pauses or choppy audio, just real connection without language barriers. So, how does it work? 🤔 The model is able to make split-second decisions to juggle speed and translation quality so conversations actually feel fluid, human, and natural. In order to do this, the model must receive and contextualize the input while simultaneously outputting the translated speech. Through this process, Gemini 3.5 Live Translate manages to stay mere seconds behind each speaker and can even maintain pacing, pitch, and intonation across extended sessions. See it in action below, or try it yourself in the Google Translate app on iOS & Android.

Today, we released Gemini 3.5 Live Translate, our latest audio model for live speech-to-speech translation. It supports over 70 languages and starts translating as soon as you start talking, streaming translations while listening to what you say next. No awkward pauses or choppy audio, just real connection without language barriers. So, how does it work? 🤔 The model is able to make split-second decisions to juggle speed and translation quality so conversations actually feel fluid, human, and natural. In order to do this, the model must receive and contextualize the input while simultaneously outputting the translated speech. Through this process, Gemini 3.5 Live Translate manages to stay mere seconds behind each speaker and can even maintain pacing, pitch, and intonation across extended sessions. See it in action below, or try it yourself in the Google Translate app on iOS & Android.

Google AI

3,988,181 Aufrufe • vor 2 Monaten

We asked Elias (Canopy Labs) about crossing the uncanny valley. Canopy Labs is building the foundation models to power digital humans indistinguishable from real ones. "The architecture matters a lot. We are starting off with an LLM that understand what humans are like." "They know that we drink water, for example. We are trying to teach them how to speak and move." "Rather than putting in text tokens, we are taking in movement and speech tokens and outputting those as well." "So eventually it (the LLM/digital human) will be able to pick up water like you do, brush its hair, rub its face when it's thinking, etc."

We asked Elias (Canopy Labs) about crossing the uncanny valley. Canopy Labs is building the foundation models to power digital humans indistinguishable from real ones. "The architecture matters a lot. We are starting off with an LLM that understand what humans are like." "They know that we drink water, for example. We are trying to teach them how to speak and move." "Rather than putting in text tokens, we are taking in movement and speech tokens and outputting those as well." "So eventually it (the LLM/digital human) will be able to pick up water like you do, brush its hair, rub its face when it's thinking, etc."

TBPN

20,249 Aufrufe • vor 1 Jahr

Mira Murati says the next AI interface is not a chatbot. It is a model that can listen, see, interrupt, and respond in real time. "The models that we work with today, they're very turn-based." "You talk, they talk, then they go off and think." "While they're thinking, it's almost like they're deaf and blind. They cannot perceive anything else about what's going on." Her new frame: interaction models. "They're not turn-based. They're more like time-based interaction." "They're continuously taking in audio, text, video, and continuously providing output." "We cut this up in chunks of 20 milliseconds... this enables you to catch things like interruptions and simultaneous speech." That is the product shift: from AI as a prompt box to AI as a high-bandwidth collaborator.

Mira Murati says the next AI interface is not a chatbot. It is a model that can listen, see, interrupt, and respond in real time. "The models that we work with today, they're very turn-based." "You talk, they talk, then they go off and think." "While they're thinking, it's almost like they're deaf and blind. They cannot perceive anything else about what's going on." Her new frame: interaction models. "They're not turn-based. They're more like time-based interaction." "They're continuously taking in audio, text, video, and continuously providing output." "We cut this up in chunks of 20 milliseconds... this enables you to catch things like interruptions and simultaneous speech." That is the product shift: from AI as a prompt box to AI as a high-bandwidth collaborator.

Karl Mehta

191,763 Aufrufe • vor 2 Monaten

Real-time translation that sounds like you 🚀 We've been building speech-to-speech simultaneous translation for a while. The newest piece is on-the-fly voice cloning: the model picks up your voice as you speak and carries it into the other language. Here's the alpha running live during our all-hands: you speak in Japanese, the room hears you in English, and it still sounds like you. It's early and the edges are rough, but this is the experience we've been building toward. Coming very soon. Demo video below 👇 #VoiceAI #SpeechAI #RealTimeTranslation #VoiceCloning #AI

Real-time translation that sounds like you 🚀 We've been building speech-to-speech simultaneous translation for a while. The newest piece is on-the-fly voice cloning: the model picks up your voice as you speak and carries it into the other language. Here's the alpha running live during our all-hands: you speak in Japanese, the room hears you in English, and it still sounds like you. It's early and the edges are rough, but this is the experience we've been building toward. Coming very soon. Demo video below 👇 #VoiceAI #SpeechAI #RealTimeTranslation #VoiceCloning #AI

Kotoba

69,405 Aufrufe • vor 10 Tagen

I've just tested the EVI 3 speech-to-speech model by Hume Hume AI, and this is the most realistic voice cloning I’ve heard. It doesn’t just clone the sound of your voice — it captures your tone, your speech patterns, your personality. Feels like your voice is thinking in real time. What’s wild is: — It’s not text-to-speech. It’s speech-to-speech. — You speak → it clones your voice + vibe — And it’s compatible with LLMs like Groq, Anthropic, Deepseek - Try talking to a voice clone: - Want more control? Customize it here: This changes how we’ll interact with AI voices. No more robotic replies — these sound human.

I've just tested the EVI 3 speech-to-speech model by Hume Hume AI, and this is the most realistic voice cloning I’ve heard. It doesn’t just clone the sound of your voice — it captures your tone, your speech patterns, your personality. Feels like your voice is thinking in real time. What’s wild is: — It’s not text-to-speech. It’s speech-to-speech. — You speak → it clones your voice + vibe — And it’s compatible with LLMs like Groq, Anthropic, Deepseek - Try talking to a voice clone: - Want more control? Customize it here: This changes how we’ll interact with AI voices. No more robotic replies — these sound human.

Aaliya

28,046 Aufrufe • vor 1 Jahr

Dear friends, Last week I was invited to give a short speech at the European Parliament in Strasbourg. In many respects, a speech in the European Parliament is a speech in the beating heart of one of the institutions at the forefront of the processes that I (we) have criticized in recent years. That's true, but at the same time I think such considerations should never stop us from going there. It is precisely with the people with whom we disagree, the people who we easily experience as our opponents, that we should try to speak. This being said, if there's one thing I don't like, it's short speeches. I prefer speeches where I have enough time to let the words visit me as they want to come at that moment and in that place. As a result, I often talk for hours and if no one stops me at some point, I’d continue even longer. Nevertheless, below you will find my 8 minute speech in the European Parliament!

Dear friends, Last week I was invited to give a short speech at the European Parliament in Strasbourg. In many respects, a speech in the European Parliament is a speech in the beating heart of one of the institutions at the forefront of the processes that I (we) have criticized in recent years. That's true, but at the same time I think such considerations should never stop us from going there. It is precisely with the people with whom we disagree, the people who we easily experience as our opponents, that we should try to speak. This being said, if there's one thing I don't like, it's short speeches. I prefer speeches where I have enough time to let the words visit me as they want to come at that moment and in that place. As a result, I often talk for hours and if no one stops me at some point, I’d continue even longer. Nevertheless, below you will find my 8 minute speech in the European Parliament!

Mattias Desmet

342,629 Aufrufe • vor 3 Jahren

BBC News speak with a lady who attended the march on Saturday in London, "I just thought it was a freedom of speech march. I think it's really important we have freedom of speech" BBC News, "Why do you feel freedom of speech is under threat? Who is threatening it?" Lady, "It's coming from all different parties" "From teachers saying you have to use the right pronouns for different genders" "It's getting the perception you can't fly your flag" "We can't accommodate everything all the time" "But we should be able to in our own country say what we want"

BBC News speak with a lady who attended the march on Saturday in London, "I just thought it was a freedom of speech march. I think it's really important we have freedom of speech" BBC News, "Why do you feel freedom of speech is under threat? Who is threatening it?" Lady, "It's coming from all different parties" "From teachers saying you have to use the right pronouns for different genders" "It's getting the perception you can't fly your flag" "We can't accommodate everything all the time" "But we should be able to in our own country say what we want"

Farrukh

172,922 Aufrufe • vor 11 Monaten

A voice agent powered by gpt-oss. Running locally on my macBook. Demo recorded in a Waymo with WiFi turned off. I'm still on my space game voice AI kick, obviously. Code link below. For conversational voice AI, you want to set the gpt-oss reasoning behavior to "low". (The default is "medium".) Notes on how to do that and a jinja template you can use are in the repo. The LLM in the demo video is the big, 120B version of gpt-oss. You can use the smaller, 20B model for this, of course. But OpenAI really did a cool thing here designing the 120B model to run in "just" 80GB of VRAM. And the llama.cpp mlx inference is fast: ~250ms TTFT. Running a big model on-device feels like a time warp into the future of AI.

A voice agent powered by gpt-oss. Running locally on my macBook. Demo recorded in a Waymo with WiFi turned off. I'm still on my space game voice AI kick, obviously. Code link below. For conversational voice AI, you want to set the gpt-oss reasoning behavior to "low". (The default is "medium".) Notes on how to do that and a jinja template you can use are in the repo. The LLM in the demo video is the big, 120B version of gpt-oss. You can use the smaller, 20B model for this, of course. But OpenAI really did a cool thing here designing the 120B model to run in "just" 80GB of VRAM. And the llama.cpp mlx inference is fast: ~250ms TTFT. Running a big model on-device feels like a time warp into the future of AI.

kwindla

202,211 Aufrufe • vor 1 Jahr

Canadian Prime Minister Mark Carney's speech at the World Economic Forum in Davos was described by the Canadian Ambassador to the U.S. Kirsten Hillman as “his view of what is happening in our world.” “I think that what it does mean for us is that we can't walk away from our principles,” Hillman said. “We can't walk away from our belief in rules that are to be abided by by everyone if they commit to them. But, at the same time, we have to be pragmatic and we have to look inward to control what we can within our own economies.”

Canadian Prime Minister Mark Carney's speech at the World Economic Forum in Davos was described by the Canadian Ambassador to the U.S. Kirsten Hillman as “his view of what is happening in our world.” “I think that what it does mean for us is that we can't walk away from our principles,” Hillman said. “We can't walk away from our belief in rules that are to be abided by by everyone if they commit to them. But, at the same time, we have to be pragmatic and we have to look inward to control what we can within our own economies.”

Face The Nation

74,761 Aufrufe • vor 7 Monaten

YouTube just took down our latest NDIS fraud investigation at the request of the business we investigated, Hope and Care. This is a massive attack on free speech in Australia. Our video is still up on X. We want to thank Elon Musk for defending free speech. We will fight this. We won’t give up. We’ve hired a really good barrister, Timothy Smartt, and we are going to fight. Thank you all for having our back. 🙏

YouTube just took down our latest NDIS fraud investigation at the request of the business we investigated, Hope and Care. This is a massive attack on free speech in Australia. Our video is still up on X. We want to thank Elon Musk for defending free speech. We will fight this. We won’t give up. We’ve hired a really good barrister, Timothy Smartt, and we are going to fight. Thank you all for having our back. 🙏

Pete Z

20,008 Aufrufe • vor 7 Tagen

ELON: FREE SPEECH IS THE FOUNDATION OF A REAL DEMOCRACY Elon lays out a point that shouldn’t be controversial… but somehow it is. He argues that you don’t get a healthy democracy by managing speech, filtering opinions, or deciding which ideas people are “allowed” to hear. Once speech is controlled in the name of safety, the system stops correcting itself and starts lying to itself. Bad ideas aren’t defeated by censorship, they’re defeated by exposure, debate, and reality. Elon’s warning is simple: when speech is suppressed, voting becomes performance art and trust collapses. Free speech isn’t a risk... losing it is. “I think it's very important for there to be an inclusive arena for free speech. It’s important that people have the reality and the perception that they are able to speak freely within the bounds of the law. A good sign is someone you don't like allowed to say something you don't like, and if that is the case then we have free speech. That is a sign of a healthy, functioning, free speech situation.” Source: EM Clips (YouTube)

ELON: FREE SPEECH IS THE FOUNDATION OF A REAL DEMOCRACY Elon lays out a point that shouldn’t be controversial… but somehow it is. He argues that you don’t get a healthy democracy by managing speech, filtering opinions, or deciding which ideas people are “allowed” to hear. Once speech is controlled in the name of safety, the system stops correcting itself and starts lying to itself. Bad ideas aren’t defeated by censorship, they’re defeated by exposure, debate, and reality. Elon’s warning is simple: when speech is suppressed, voting becomes performance art and trust collapses. Free speech isn’t a risk... losing it is. “I think it's very important for there to be an inclusive arena for free speech. It’s important that people have the reality and the perception that they are able to speak freely within the bounds of the law. A good sign is someone you don't like allowed to say something you don't like, and if that is the case then we have free speech. That is a sign of a healthy, functioning, free speech situation.” Source: EM Clips (YouTube)

Mario Nawfal

37,917 Aufrufe • vor 8 Monaten

Today we launched Gemini 3.1 Flash TTS, our most expressive and controllable text-to-speech model yet. This launch [excitement] includes audio tags! 🗣🏷 Audio tags [explanatory] are a seamless way to guide vocal style, pace, and delivery using natural language commands embedded directly in your text. Want a different tempo or tone? [amazement] Just tag the audio to steer the AI-speech output! The model supports 70+ languages (24 of which are high-quality evaluated languages, including: Japanese, Hindi, and Arabic). Watch the audio tags in action in the demo below ↓

Today we launched Gemini 3.1 Flash TTS, our most expressive and controllable text-to-speech model yet. This launch [excitement] includes audio tags! 🗣🏷 Audio tags [explanatory] are a seamless way to guide vocal style, pace, and delivery using natural language commands embedded directly in your text. Want a different tempo or tone? [amazement] Just tag the audio to steer the AI-speech output! The model supports 70+ languages (24 of which are high-quality evaluated languages, including: Japanese, Hindi, and Arabic). Watch the audio tags in action in the demo below ↓

Google AI

203,245 Aufrufe • vor 4 Monaten

LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models paper page: github: Recent advancements in text-to-image generation with diffusion models have yielded remarkable results synthesizing highly realistic and diverse images. However, these models still encounter difficulties when generating images from prompts that demand spatial or common sense reasoning. We propose to equip diffusion models with enhanced reasoning capabilities by using off-the-shelf pretrained large language models (LLMs) in a novel two-stage generation process. First, we adapt an LLM to be a text-guided layout generator through in-context learning. When provided with an image prompt, an LLM outputs a scene layout in the form of bounding boxes along with corresponding individual descriptions. Second, we steer a diffusion model with a novel controller to generate images conditioned on the layout. Both stages utilize frozen pretrained models without any LLM or diffusion model parameter optimization. We validate the superiority of our design by demonstrating its ability to outperform the base diffusion model in accurately generating images according to prompts that necessitate both language and spatial reasoning. Additionally, our method naturally allows dialog-based scene specification and is able to handle prompts in a language that is not well-supported by the underlying diffusion model.

LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models paper page: github: Recent advancements in text-to-image generation with diffusion models have yielded remarkable results synthesizing highly realistic and diverse images. However, these models still encounter difficulties when generating images from prompts that demand spatial or common sense reasoning. We propose to equip diffusion models with enhanced reasoning capabilities by using off-the-shelf pretrained large language models (LLMs) in a novel two-stage generation process. First, we adapt an LLM to be a text-guided layout generator through in-context learning. When provided with an image prompt, an LLM outputs a scene layout in the form of bounding boxes along with corresponding individual descriptions. Second, we steer a diffusion model with a novel controller to generate images conditioned on the layout. Both stages utilize frozen pretrained models without any LLM or diffusion model parameter optimization. We validate the superiority of our design by demonstrating its ability to outperform the base diffusion model in accurately generating images according to prompts that necessitate both language and spatial reasoning. Additionally, our method naturally allows dialog-based scene specification and is able to handle prompts in a language that is not well-supported by the underlying diffusion model.

AK

83,657 Aufrufe • vor 3 Jahren

These black naturalized Muslim politicians think they have the right to police what white Republicans are allowed to say. They lecture native-born Americans on speech, demand we self-censor, and act like they’re the moral authority in a country they didn’t create. This is what happens when you import people from incompatible cultures, give them citizenship, and then watch them try to control the speech of the population whose ancestors actually built this nation. Free speech isn’t a privilege they get to grant or revoke. It’s an American right — and it doesn’t belong to recent arrivals pushing foreign speech codes. Assimilation was supposed to work the other way around.

These black naturalized Muslim politicians think they have the right to police what white Republicans are allowed to say. They lecture native-born Americans on speech, demand we self-censor, and act like they’re the moral authority in a country they didn’t create. This is what happens when you import people from incompatible cultures, give them citizenship, and then watch them try to control the speech of the population whose ancestors actually built this nation. Free speech isn’t a privilege they get to grant or revoke. It’s an American right — and it doesn’t belong to recent arrivals pushing foreign speech codes. Assimilation was supposed to work the other way around.

GRANDPA’s FREE ADVICE

51,712 Aufrufe • vor 3 Monaten