Tag

Qwen3.8-27B — OBLITERATED

An uncensored, weight-modified variant of Qwen3.8-27B that surgically removes the model's refusal directions to produce 0% refusals while aiming to preserve or improve capability. Uses complementary abliteration blending (SVD + LEACE blend) and ships with recommended greedy inference settings; intended for AI-safety research and red‑teaming, not for causing harm.

Ornith-1.5-9B-GGUF

A 9B dense reasoning LLM optimized for single‑GPU deployment and terminal-based coding agents, with long-context support (up to 262,144 tokens) and GGUF/quantized builds for edge/mobile. Strong on coding and agentic benchmarks.

EnvHarness: Awakening Static Worlds for Agent Learning

Wraps static, hand-built environments with a programmable plug-in harness that reshapes environment behavior without changing underlying logic. EnvRigger automates diagnosis and synthesis of harness components from agent failure trajectories, validating edits via fresh rollouts to improve agent success and efficiency.

Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs

Treats human annotations as oracle rollouts and separates them from on-policy baselines to improve reinforcement learning for video multimodal LLMs. Key features include a decoupled advantage estimator, sign-balanced pruning, and scalable gains across model sizes and data budgets.

VGI-Bench: Probing Visual Intelligence in Video Generation Models

Evaluates visual reasoning in video generation models using 27 photorealistic tasks (810 instances), a two-level taxonomy of domains and skill tags, and task designs that enforce valid intermediate trajectories and calibrated difficulty.

WithEveryone: Unified Planning and Identity Grounding for Group Image Generation

Generates group images that bind up to ten reference identities to distinct people and locations by predicting an explicit identity–layout plan and supervising faces with Layout-Grounded ID Loss. Improves identity fidelity while cutting copy-paste duplication; suited for multi-person image synthesis but requires identity-annotated face regions and paired training data.

OmniAssistBench: Assistant-style Interaction Benchmark for Omni-LLMs

Benchmarks assistant-style, multi-turn interaction for omni-modal LLMs on real-time video by reverse-engineering Internet clips into guided multi-turn interactions. It provides predefined priors and segment-level constraints so models must follow exact routes while being evaluated on answer correctness, timing, visual-prompt handling, and context retention.

Spark-X2.5-4B

A 4B-parameter on-device general-purpose LLM for chat, writing, translation, coding and agentic workflows with native 1,000,000-token context. Uses a hybrid attention design to enable long-context efficiency, pretrained on ~20T tokens, and compatible with vLLM, llama.cpp, Ollama and LM Studio.

Pipecat PhoneLLM Alpha 1

Open-weights LLM fine-tuned for phone-based voice agents that prioritizes low latency and reliable tool/function calling. Based on NVIDIA Nemotron 3 Nano (30B total, 3.5B active), supports very long contexts (262,144 tokens) and recommends temperature=0 with thinking disabled for deployment.

Qwen3.8-Flash-Next

Experimental open-weight multimodal LLM preview designed for long-context, agentic workloads. It introduces hybrid sparse attention (QSA), gated residual streams, and large offloadable n‑gram embeddings (51B) alongside a high-sparsity MoE (125B total, 6B active) to trade memory for runtime efficiency and improved long-horizon reasoning.

MobilePA-Bench: Benchmarking Mobile Planner Agents on Complex Real-World Tasks

Assesses mobile planning agents' ability to call tools, plan long-horizon workflows, and coordinate sub-agents in realistic, interactive phone scenarios via a stateful executable sandbox. Covers 13 domains, 212 tools, evidence-based verification, and tests memory, skill usage, permission and runtime constraints.

AutoSaddler: Automatic Harness Optimization with Durable Updates from Agent Execution Traces

Automatically optimizes runtime harnesses for LLM agents by diagnosing failure traces and iteratively applying structured, generalizable patches. Combines batch-based failure diagnosis, code-like patch generation across prompts/tools/middleware, and validation-aware selection to raise long-horizon task success on multiple benchmarks.