2026-11-05

Psychotherapy clients may experience distress before they can coherently describe it, and their expression changes with emotion, perceived safety, and trust. Large language model-based client simulators often rely on clinically organized case descriptions, which can encourage responses explaining the client's difficulties more clearly than their current understanding warrants. We propose Pandora, a psychotherapy client simulation framework that models how psychological experience becomes situate

🤖Pandora is a psychotherapy client simulation framework that models evolving psychological and relational states to generate more authentic, individually aligned expressions and reduce AI-like responses.

Large reasoning models achieve strong performance on challenging tasks, but their long chain-of-thought often incurs substantial inference costs by continuing to deliberate after sufficient information has been obtained. Existing reasoning compression methods primarily operate on reasoning trajectories, paying less attention to the local decision of whether further reasoning is necessary given the current state. We propose LoCo, a local preference learning method for reasoning compression. LoCo

🤖LoCo uses local preference learning to teach reasoning models when to stop deliberating, reducing output length substantially while preserving or improving accuracy across math and code tasks.

Long-form multi-shot video editing requires an intended edit to remain coherent across abrupt changes in scene, viewpoint, and subject appearance, while processing substantially longer visual context than conventional single-shot editors. We introduce MoviEdit, an end-to-end framework for scalable long-form multi-shot video editing that jointly addresses the challenges of data, modeling, and evaluation. To provide cross-shot supervision data at scale, we develop automatic data-generation pipelin

🤖MoviEdit is an end-to-end framework for long-form multi-shot video editing that uses cascaded bidirectional-autoregressive modeling and a new benchmark to maintain coherence across scenes while reducing manual data annotation.

Video generation has progressed from isolated clips to coherent short-form audiovisual sequences, and the bottleneck is shifting from rendering to semantic control. This report summarizes the observations and insights on multimodal understanding gained from successive generations of Kling. We argue that generation quality is the projection of multimodal understanding through the entire data--conditioning--alignment--evaluation chain, and we examine this chain module by module. Kling-MLLM, a shar

🤖Kling's multimodal understanding stack links caption density, perceptual text encoding, reward modeling, and evaluation protocols to improve controllable video generation.

Learning a universal action representation from video requires modeling dynamics that are consistent across different executions of the same action yet invariant to changes in embodiment and appearance. Existing latent action models infer actions from visual transitions, but their representations often entangle the underlying action with irrelevant visual variations, limiting transfer across embodiments. We introduce DreamX, which repurposes a pretrained video diffusion model as a universal late

🤖DreamX leverages a pretrained video diffusion model to learn compact, appearance-invariant latent actions that enable cross-embodiment transfer and efficient policy learning.

To give you some context on the project. I'm a solo founder and I use AI heavily in my work. The idea came from wanting players to discover cities. Each city has its own history, so every case is set in a real city with real public places. The crime and the people are on other hand invented. The part that I care most is the playable aspect of the game, a model plays the detective and must solve the case before it goes live. As of today: it's free on Android, the iOS version is still waiting to b

During its busiest week last quarter, Uber said only four people booked a ride using an AI agent.

Article URL: Comments URL: Points: 106 # Comments: 15

The milestone comes a year after Snapchat announced a controversial limit on free storage for its Memories feature and informed users it would start requiring users to pay $1.99 per month for additional storage or subscribe to Snapchat+ to retain their Memories.

While it's not yet clear what kind of product the smartphone startup is cooking up, Nothing's CEO said the product is designed to leverage AI for productivity gains.