Daily papers of 29 Oct 2026

Daily Papers

Here is the selection of papers for today (29 Oct):

• Efficient Streaming Audio-Visual Target Speaker Extraction for Real-World Acoustic Scenes (149 ▲)
• OmniShowcase: Omnidirectional Subject-Consistent Video Generation from Multi-View Images (44 ▲)
• Sensorimotor Alignment: A Platonic Proxy for Embodied Policy Success (20 ▲)
• TAO: Tool-Aware Joint Scheduling for LLM-Based Agentic Serving (16 ▲)
• RealCLI: Toward a Unified Evaluation of Human-Agent Collaboration for CLI Agents (15 ▲)
• TauIndianBankBench: Procedure-Aware, Action-Oriented Evaluation of Tool-Using Conversational Agents (8 ▲)
• Amortizing Sequential Experimental Design in Reasoning LLMs (5 ▲)
• LongZero: Enhancing Long-Context Reasoning in LLMs from Zero Data (4 ▲)
• CausGround: Causal Interaction Grounding for Adaptive Embodied Planning (3 ▲)
• Evaluating DeepSeek V4.1 Flash-1017 for loss of control and harmful manipulation risks (2 ▲)
• HuGe: Scaling Humanoid Generalist Vision-Language-Action Models with Egocentric Experience (1 ▲)
• Instruction Capacity: Behavior and Degradation of Language Models under Controlled Load (1 ▲)
• To view more checkout today's Daily Paper page.

NEW - I'm opening Daily Papers! If you're a researcher you can now submit your peers' papers to be featured in Daily Papers directly. Use this page to do so: huggingface.co/papers/submit.

See you soon,
AK and the research community