AI Model2026
Generates unified 768‑dimensional embeddings for text (including code), images, video and audio to enable cross‑modal semantic search and retrieval. Supports task instruction prefixes, Matryoshka truncation to 128/256/512/768 dims, and modular encoders for on‑device use under an Apache‑2.0 license.
AI Model2026
Compresses a 27B-class multimodal model into end-to-end ternary weights to run 27B reasoning on-device: 5.9–8.6 GB deployed footprint, 262K-token context, ~98.2% of FP16 benchmark performance; ships MLX and GGUF packs and runs on Apple MLX and CUDA.
AI Model2026
Turns Qwen3.5 into a 3-way NLI cross-encoder (entailment/contradiction/neutral) for zero-shot reranking, grading, content guarding, or action selection. Provides a pretrained Qwen3.5-4B checkpoint, helper utilities (OpenJevCrossEncoder, LatentMLPHead), and optional 35B MoE latent heads for per-task scoring.
Introduces physical rank consistency (PRC) and ActionPiece, a learned action tokenizer that preserves local physical relationships via joint supervision of representation learning and quantization, improving autoregressive vision-language-action policy performance across multiple benchmarks.
Enables specifying exact 24-bit hex colors for object-level image generation and editing via a unified prompt interface, using a Paint-500K dataset and timestep-gated pure-color anchors to improve color fidelity.
Provides a domain-agnostic world-modeling framework that factorizes latent targets into orthogonal predictive components, with dedicated prediction branches and synthesis for multi-domain forecasting and intervention. Demonstrates improved dynamics and long-horizon rollouts across seven domains and includes experimental biological validation.
AI Video Papers2026
Zhenchen Tang, Yang Li +7New Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, School of Artificial Intelligence, University of Chinese Academy of Sciences +2
Introduces a rubric-based approach for video reward modeling that generates explicit, query-adaptive evaluation criteria before scoring to reduce scalar drift; proposes RGPO, a two-stage training (seed warm-up + joint optimization) that achieves strong pointwise and pairwise evaluation with high data efficiency.
Embodied AI2026
Uses a compact discrete-action interface (translation, rotation, gripper) to let frozen vision–language models control robots in closed-loop, and leverages in-context (one-shot) demonstrations to substantially improve manipulation success without robot-specific training.
Teaches vision-language models to predict and integrate physical-world state transitions from interaction trajectories (observation → action → next observation). Introduces a three-level curriculum and the LSI-108K dataset, and applies supervised fine-tuning plus on-policy distillation to improve local transition modeling and long-horizon spatial integration.
AI Model2026
Converts multimodal inputs (text, image, audio, video) plus a question and options into calibrated probability distributions over choices. Built on Gemma 4 12B with a 30,000-question fine-tune, optimized for per-question decision classification and low-latency inference (Apache-2.0).
AI Agent Papers2026
Ruixun Liu, Yuxuan Wang +11School of Intelligence Science and Technology, Peking University, State Key Laboratory of General Artificial Intelligence, Peking University +2
Provides a unified benchmark and a spatially aware omni-modal model for spatial audio-visual reasoning in embodied agents — OmniEchoBench (197 scenes, 2,972 QA pairs; 900 FOA-based navigation tasks) plus OmniEcho, which adds an FOA spatial encoder to a pretrained semantic audio pathway to enable spatial QA and sound-guided navigation.
Hangyu Ran, Yuhao Zheng +3Ant Group, The Hong Kong University of Science and Technology (Guangzhou) +2
Converts natural-language SVG instructions into instance-aware six-item rubrics and uses a vision–language judge to score rendered SVGs item-by-item as dense RL rewards. Produces stronger human alignment and lifts benchmark rubric scores substantially on MMSVG datasets.