· ai
[Paper] Single-Stage Huffman Encoder for ML Compression
Training and serving Large Language Models (LLMs) require partitioning data across multiple accelerators, where collective operations are frequently bottlenecke...
-
- · ai
[Paper] Detecting Winning Arguments with Large Language Models and Persuasion Strategies
Detecting persuasion in argumentative text is a challenging task with important implications for understanding human communication. This work investigates the r...
- · ai
[Paper] PACEvolve: Enabling Long-Horizon Progress-Aware Consistent Evolution
Large Language Models (LLMs) have emerged as powerful operators for evolutionary search, yet the design of efficient search scaffolds remains ad hoc. While prom...
- · ai
[Paper] Multi-Property Synthesis
We study LTLf synthesis with multiple properties, where satisfying all properties may be impossible. Instead of enumerating subsets of properties, we compute in...
- · ai
[Paper] CURVE: A Benchmark for Cultural and Multilingual Long Video Reasoning
Recent advancements in video models have shown tremendous progress, particularly in long video understanding. However, current benchmarks predominantly feature ...
- · ai
[Paper] Influential Training Data Retrieval for Explaining Verbalized Confidence of LLMs
Large language models (LLMs) can increase users' perceived trust by verbalizing confidence in their outputs. However, prior work has shown that LLMs are often o...
- · it
Why MongoDB thinks better retrieval — not bigger models — is the key to trustworthy enterprise AI
Agentic systems and enterprise search depend on strong data retrieval that works efficiently and accurately. Database provider MongoDB thinks its newest embeddi...
- · ai
[Paper] CoMoVi: Co-Generation of 3D Human Motions and Realistic Videos
In this paper, we find that the generation of 3D human motions and 2D human videos is intrinsically coupled. 3D motions provide the structural prior for plausib...
- · ai
**Unlocking Optimal Performance: The AI-Powered Transformati
In 2024, I had the privilege of collaborating with the Miami Dolphins' Swim Coach as they embarked on a mission to optimize their competitive edge in the aquati...
- · ai
[Paper] Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding
Today's strongest video-language models (VLMs) remain proprietary. The strongest open-weight models either rely on synthetic data from proprietary VLMs, effecti...
- · ai
[Paper] Multi-Objective Pareto-Front Optimization for Efficient Adaptive VVC Streaming
Adaptive video streaming has facilitated improved video streaming over the past years. A balance among coding performance objectives such as bitrate, video qual...
- · ai
[Paper] RSATalker: Realistic Socially-Aware Talking Head Generation for Multi-Turn Conversation
Talking head generation is increasingly important in virtual reality (VR), especially for social scenarios involving multi-turn conversation. Existing approache...