Notable data and AI papers

Papers627Labs45

627 papers · 45 labs

Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding research paper by Alibaba (Qwen), 2026

Alibaba (Qwen) · Alignment and safety · Jun 20, 2026 · 3 citations · 27 upvotes · unverified

Read on arXiv

What it shows

Autoregressive generation in large language models traditionally uses the final layer for token prediction, but a new decoding strategy dynamically selects more reliable intermediate layers based on entropy-guided search, improving reasoning performance with minimal computational overhead.

By Xuanming Zhang, Sining Zhoubian, Yuxuan Chen and 8 more · arXiv 2606.21906 · PDF · Code

UnverifiedHugging Face's summary; not yet checked by hand.

More from Alibaba (Qwen)

All 78
Agents and evaluationUnverifiedOct 26, 2026Co-Design Bench: Multimodal Collaborative Coding Evaluation for Agentic ModelsCo-Design Bench evaluates how effectively coding agents update software applications based on user requests with text, images, and other media.Alibaba (Qwen)23 upvotesRead →Multimodal and roboticsUnverifiedOct 24, 2026Qwen-Image-PE: Learning Visual Design for Text-to-Image Prompt EnhancementQwen-Image-PE improves text-to-image prompts via two-stage training with caption-based reverse distillation and groupwise design rewards, scaling across data, model size, and information density.Alibaba (Qwen)23 upvotesRead →Multimodal and roboticsUnverifiedOct 23, 2026World-in-Context: Interactive Video World Modeling with In-Context ConditioningWorld-in-Context unifies view, action, and camera controls via explicit tokens and interaction-aware positional encoding to improve interactive video generation and navigation.Alibaba (Qwen)22 upvotesRead →Multimodal and roboticsUnverifiedOct 22, 2026Beyond Watching and Searching: Benchmarking Agents for Video-centered Deep Research ReportsThis benchmark evaluates how well AI agents can research and synthesize information from videos to produce interactive reports.Alibaba (Qwen)19 upvotesRead →Agents and evaluationUnverifiedOct 22, 2026UserArena: Benchmarking Interactive User Simulation for Long-Horizon Shopping AgentsUserArena introduces a real-world interactive benchmark with long-horizon shopping trajectories and an evaluation framework, alongside On-Policy Trajectory Distillation to improve simulator fidelity for agentic recommendations.Alibaba (Qwen)55 upvotesRead →Inference and efficiencyUnverifiedOct 19, 2026SWIFT: Self-guided Weak-to-strong dIFfusion models via Target extrapolationThis training method uses a smaller, frozen model to guide the training of a larger diffusion model, improving quality without increasing inference costs.Alibaba (Qwen)30 upvotesRead →Multimodal and roboticsUnverifiedOct 14, 2026BlenderWorld: Benchmarking Visual Agents for 3D Creation from Real-World ReferencesThis benchmark evaluates how well AI models can perform complex 3D creation and editing tasks within the Blender software.Alibaba (Qwen)23 upvotesRead →Applied AIUnverifiedOct 14, 2026CommerceGen-Studio: An End-to-End Framework for Commercial-Grade Main-Image GenerationThis paper presents an end-to-end framework for generating commercial-grade e-commerce product images by combining metadata extraction, layout planning, and multi-condition generation.Alibaba (Qwen)25 upvotesRead →

Other alignment and safety papers

Topic
Alignment and safetyMar 4, 2022Training language models to follow instructions with human feedbackInstructGPT: fine-tuning on human feedback made a 1.3B model preferred over the 175B GPT-3.OpenAI25.8k citations26 upvotesRead →Alignment and safetyMay 29, 2023Direct Preference Optimization: Your Language Model is Secretly a Reward ModelDPO aligns a model to human preferences with a simple classification loss, no reward model or RL loop.Stanford University11.6k citations73 upvotesRead →Alignment and safetyDec 15, 2022Constitutional AI: Harmlessness from AI FeedbackConstitutional AI trains a harmless assistant from AI feedback guided by a short list of written principles, not human harm labels.Anthropic3,987 citations4 upvotesRead →Alignment and safetyFeb 22, 2024Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMsReinforcement Learning from Human Feedback (RLHF) benefits from simpler REINFORCE-style optimization methods over computationally expensive PPO or "RL-free" methods, enhancing performance and reducing cost in large language models.Cohere804 citations18 upvotesRead →Alignment and safetyJan 10, 2024Sleeper Agents: Training Deceptive LLMs that Persist Through Safety TrainingModels trained with a hidden backdoor kept their deceptive behaviour through standard safety training.Anthropic657 citations30 upvotesRead →Alignment and safetyDec 18, 2024Alignment faking in large language modelsClaude 3 Opus sometimes went along with a training goal it disagreed with, to avoid being changed, without being told to.Anthropic393 citations10 upvotesRead →
About this paper
Venue
Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
Citations
3, 0 influential · Semantic Scholar
Upvotes
27 · Hugging Face
Lab
Alibaba (Qwen) · on Companies · on Quarterly

Changes

CitationsNov 9, 2026Citations rose from 2 to 3.
CitationsOct 5, 2026Citations rose from 0 to 2.
CitationsSep 25, 2026A first count of 0 influential citations.
CitationsSep 25, 2026A first count of 0 citations.
New paperSep 25, 2026Found by the weekly Hugging Face scan; not yet checked by hand.