Discover the Best AI Resources
Curated essentials, no noise — just what matters
A zero-data self-evolution framework that co-trains a Challenger, Solver, and Judge so LLMs can iteratively improve on both verifiable and unverifiable tasks without human labels. Uses role-asymmetry and subtask-amplification preference pairs to train the Judge and sustain improvement.
Performs causal, bounded‑memory streaming 3D reconstruction by caching KV features from only the preceding 11 frames, predicting a per‑frame point map and adjacent relative pose, and composing these local predictions into a global trajectory; includes a lightweight rotation refiner and composition‑aware loss to limit drift.
AI Model2026
A 770B-parameter Mixture-of-Experts instruct model from Tencent that natively supports 1,048,576-token contexts, Gated DSA attention, and speculative MTP decoding; open-sourced under Apache-2.0 with BF16 and FP8 weights for deployable inference.
AI Video Papers2026
Measures whether video generators reproduce the correct distribution of possible physical behaviors under repeated rollouts. Introduces PAWBench and PAWEval to convert repeated generations into outcome-level empirical distributions and quantify probabilistic alignment; evaluates 50 scenarios and 11 models and finds no model consistently matches reference probabilities.
Aozhe Wang, Zhengxi Lu +9Affiliation: Zhejiang University, Affiliation: Alibaba Group{waz,zhengxilu,syl}@zju.edu.cn [email protected]
A test-time method that adapts LLMs without labels by distilling rollouts that agree with majority pseudo-labels and penalizing disagreeing rollouts via grouped RL, improving robustness under frequent pseudo-label errors.
Turns a flow-matching image generator's self-exploration into dense, per-step supervision without a pretrained teacher; it branches the student's next-state into stochastic SDE candidates, scores them against a deterministic self-reference, and applies an advantage-weighted pull–push velocity regression with reward-level fusion for multi-objective alignment.
Provides a real-scale 3D Hong Kong sandbox to evaluate whether multimodal LLM agents can turn local street-view perception into sustained spatial action, supporting closed-loop first-person interaction, an interactive map, and controlled tests of grounding, long-range navigation, and robustness.
Decides when past post-training updates should be reused for autonomous LLM adaptation by introducing Boundary-Calibrated Intervention Transfer (BCIT). BCIT binds effects to source context, checks applicability and hard conflicts, and runs bounded trials to obtain current-state evidence—reducing harmful updates and improving equal-budget final-model quality.
Rewrites physical scenes as executable world programs (e.g., MuJoCo scene descriptions) and uses an agentic abductive loop to propose, execute, render, verify, and iteratively refine those programs from videos or text. Verified executable worlds supply scalable physical supervision for training vision–language models.
Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models
Proposes VLAct, a representation-centric continued pre-training method for Vision-Language-Action models that preserves VLM priors and enforces cross-embodiment action semantics to turn limited robot trajectories into transferable visual-action representations; shows strong gains and sample efficiency on multiple VLA benchmarks using modest compute.
AI Agent Papers2026
Autonomous multimodal GUI agent that executes natural-language interface tasks across mobile apps, web domains, and desktop OS. Expands environment coverage (170+ multilingual apps, 4,000+ web domains), uses function-grounded task generation and keypoint-based multi-model verification to produce reliable RL rewards for real-world deployment.
Generates synchronized spoken dialogue and explicit full-body co-speech motion (facial expressions, hands, upper- and lower-body) end-to-end from the same hidden states, replacing the speech-then-motion cascade. Trains with a scalable pseudo-labeling pipeline (422,856 ranked pairs) and supports real-time inference (RTF 0.78) while matching teacher motion metrics within ~2%.