Nachrichten
T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT
arXiv:2505.00703v2 Announce Type: replace-cross Abstract: Recent advancements in large language models have demonstrated how chain-of-thought...
System Report for CCL25-Eval Task 10: SRAG-MAV for Fine-Grained Chinese Hate Speech Recognition
arXiv:2507.18580v1 Announce Type: new Abstract: This paper presents our system for CCL25-Eval Task 10, addressing...
SynPref-40M and Skywork-Reward-V2: Scalable Human-AI Alignment for State-of-the-Art Reward Models
Understanding Limitations of Current Reward Models Although reward models play a crucial role in Reinforcement...
SynapseRoute: An Auto-Route Switching Framework on Dual-State Large Language Model
arXiv:2507.02822v1 Announce Type: new Abstract: With the widespread adoption of large language models (LLMs) in...
SwiReasoning: Entropy-Driven Alternation of Latent and Explicit Chain-of-Thought for Reasoning LLMs
SwiReasoning is a decoding-time framework that lets a reasoning LLM decide when to think in...
SWE-Bench Performance Reaches 50.8% Without Tool Use: A Case for Monolithic State-in-Context Agents
Recent advancements in LM agents have shown promising potential for automating intricate real-world tasks. These...
Surprise Calibration for Better In-Context Learning
arXiv:2506.12796v1 Announce Type: new Abstract: In-context learning (ICL) has emerged as a powerful paradigm for...
Support or Refute: Analyzing the Stance of Evidence to Detect Out-of-Context Mis- and Disinformation
arXiv:2311.01766v5 Announce Type: replace Abstract: Mis- and disinformation online have become a major societal problem...
Superintelligence: Unlocking the Mysteries of the Future
Imagine a future where machines don’t just outperform humans in specific tasks but fundamentally outthink...
StreamTensor: A PyTorch-to-Accelerator Compiler that Streams LLM Intermediates Across FPGA Dataflows
Why treat LLM inference as batched kernels to DRAM when a dataflow compiler can pipe...
Streaming Sequence-to-Sequence Learning with Delayed Streams Modeling
arXiv:2509.08753v1 Announce Type: new Abstract: We introduce Delayed Streams Modeling (DSM), a flexible formulation for...
Stop guessing why your LLMs break: Anthropic’s new tool shows you exactly what goes wrong
Anthropic’s open-source circuit tracing tool can help developers debug, optimize, and control AI for reliable...
