Microsoft has released HARC-Qwen2.5-7B-Instruct, a fine-tuned version of Qwen2.5-7B-Instruct optimized for safety and alignment in conversational AI. The model is a transformer-based text-generation model, available on Hugging Face under the Apache 2.0 license. It is distributed in safetensors format and is compatible with text-generation-inference and Hugging Face endpoints. The release is associated with the paper arXiv:2607.00572.
Microsoft released HARC-Llama-3.1-8B-Instruct on Hugging Face. It is a text-generation model built on Meta's Llama 3.1 8B Instruct. Repository tags indicate a focus on safety, alignment, and conversational use. The model card provides no benchmarks, training details, or specific capability claims. It is distributed under the Llama 3.1 license.
This paper reveals that dense on-policy self-distillation (SDPO) accelerates in-domain specialization under stable teacher signals, but causes severe forgetting and even complete collapse during continual post-training. In contrast, on-policy reinforcement learning methods like GRPO adapt more conservatively and better preserve prior capabilities. Denser self-distillation induces larger drift in parameter and response spaces, and amplifies high-frequency formatting artifacts through a self-reinforcing teacher-student loop. The findings caution that on-policy data alone is insufficient for continual learning, and dense self-distillation should not be treated as a default stabilizer.
WorldDirector is a controllable video world model framework that explicitly decouples semantic motion orchestration from visual generation. It uses a large language model to coordinate 3D object trajectories and camera movements, then employs these trajectories as control signals for a video generator. This design ensures strict physical consistency, stable appearance, and persistent memory of dynamic objects—maintaining their exact visual identity even when they re-enter a scene after long occlusions. The framework supports unrestrained viewpoint exploration and can synthesize complex, extended events with high controllability.
The paper introduces AgenticSTS, a bounded-memory contract for long-horizon LLM agents where every decision is made from a fresh user message constructed via typed retrieval, appending no raw cross-decision transcript and bounding the prompt independently of run length. This contract is instantiated in the closed-rule deck-building game Slay the Spire 2, which requires hundreds of tactical and strategic decisions. A public online benchmark of frontier LLMs on the same game achieved zero wins at the lowest difficulty, while the developer-reported human win rate is 16%, indicating the task is hard but not saturated. In an ablation within the authors' harness, a baseline with no triggered strategic skills won 3 out of 10 games, and enabling the skill layer raised the wins to 6 out of 10 (directional, Fisher exact p≈0.37). The authors release a reproducible testbed comprising 298 completed trajectories with condition tags, frozen memory/skill snapshots, prompt records, and analysis scripts.
The paper adapts a mixture-of-experts discrete diffusion language model, DiffusionGemma-26B, and benchmarks it against the autoregressive Gemma-4-26B on medical visual question answering. Using the same LoRA fine-tuning recipe, the diffusion model matches or exceeds AR performance, scored by a verbosity-robust LLM judge, while decoding 3.5–4.4× faster. The fine-tuned model (3.8B active parameters) is competitive with frontier vision-language models. Crucially, the diffusion paradigm enables any-order infill: a radiologist can correct parts of a report and the model generates the text between them, a capability inherent to diffusion that autoregressive models cannot easily replicate. This suits real-world radiology reports, which often vary in style and completeness across clinicians and institutions.