SE-Bench: Benchmarking Self-Evolution with Knowledge Internalization Paper • 2602.04811 • Published 29 days ago • 2
UM-Text: A Unified Multimodal Model for Image Understanding Paper • 2601.08321 • Published Jan 13 • 11
ResTok: Learning Hierarchical Residuals in 1D Visual Tokenizers for Autoregressive Image Generation Paper • 2601.03955 • Published Jan 7 • 3
FlowBlending: Stage-Aware Multi-Model Sampling for Fast and High-Fidelity Video Generation Paper • 2512.24724 • Published Dec 31, 2025 • 7
Dream2Flow: Bridging Video Generation and Open-World Manipulation with 3D Object Flow Paper • 2512.24766 • Published Dec 31, 2025 • 9
What matters for Representation Alignment: Global Information or Spatial Structure? Paper • 2512.10794 • Published Dec 11, 2025 • 9
TV2TV: A Unified Framework for Interleaved Language and Video Generation Paper • 2512.05103 • Published Dec 4, 2025 • 20
ThreadWeaver: Adaptive Threading for Efficient Parallel Reasoning in Language Models Paper • 2512.07843 • Published Nov 24, 2025 • 22
BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution Paper • 2510.08697 • Published Oct 9, 2025 • 39
view post Post 52299 Google drops Gemini 2.0 Flash Thinkinga new experimental model that unlocks stronger reasoning capabilities and shows its thoughts. The model plans (with thoughts visible), can solve complex problems with Flash speeds, and morenow available in anychat, try it out: https://huggingface.co/spaces/akhaliq/anychat See translation 5 replies · 🚀 12 12 🔥 6 6 👍 4 4 👀 2 2 + Reply
Token-level and sequence-level loss smoothing for RNN language models Paper • 1805.05062 • Published May 14, 2018
Efficient Wait-k Models for Simultaneous Machine Translation Paper • 2005.08595 • Published May 18, 2020
Added Toxicity Mitigation at Inference Time for Multimodal and Massively Multilingual Translation Paper • 2311.06532 • Published Nov 11, 2023