archive
Every paper Pith has read. Search by title, abstract, or pith.
22229 papers in cs · page 1
-
BlitzGS is a distributed 3D Gaussian Splatting system that shards Gaussians by index…
BlitzGS: City-Scale Gaussian Splatting at Lightning Speed
-
Extended SBA adds two-layer architecture for strategic scenarios
Extended Scenario Bundle Analysis: A Formal Framework for Strategic Scenario Modeling
-
PoisonCap gives CHERI strict use-after-free at zero overhead
PoisonCap: Efficient Hierarchical Temporal Safety for CHERI
-
Heterogeneous solvers up to 32% faster than GPU-only for big matrices
Comparing the Performance of Heterogeneous Conjugate Gradient and Cholesky Solvers on Various Hardware Using SYCL
-
Conventions enable composition of policies for multiple omega-regular goals
Decoupled Planning for Multiple Omega-Regular Objectives
-
Benchmark shows top multimodal models lag on e-commerce
OxyEcomBench: Benchmarking Multimodal Foundation Models across E-Commerce Ecosystems
-
This paper introduces DESBench
When Does Hierarchy Help? Benchmarking Agent Coordination in Event-Driven Industrial Scheduling
-
Coupled latents produce 3D assets with built-in skeletons and skinning
Rigel3D: Rig-aware Latents for Animation-Ready 3D Asset Generation
-
Multi-agent system automates VC due diligence
A Multi-Agent Orchestration Framework for Venture Capital Due Diligence
-
Shapley values fairly assign responsibility in stochastic games
Counterfactual Reasoning for Causal Responsibility Attribution in Probabilistic Multi-Agent Systems
-
Graph doubling maps ultrabubbles to weak superbubbles in linear time
The Power of Graph Doubling: Computing Ultrabubbles in a Bidirected Graph by Reducing to Weak Superbubbles
-
Spiking neurons split frequency choice from timing adjustment
FiTS: Interpretable Spiking Neurons via Frequency Selectivity and Temporal Shaping
-
The paper introduces Dual-Ordering Prioritized Planning (DOPP)
Conveyor Parcel Routing with Order-Contiguous Arrivals
-
Mamba forecaster decodes mouse choice from spikes at 76 percent
Implicit Behavioral Decoding from Next-Step Spike Forecasts at Population Scale
-
Spike forecasting ranks brain regions consistently across models
SpikeProphecy: A Large-Scale Benchmark for Autoregressive Neural Population Forecasting
-
Unified model makes understanding and generation emerge together
SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture
-
Synthetic data trains 4B model to beat larger open-source agents
Covering Human Action Space for Computer Use: Data Synthesis and Benchmark
-
Forearm guidance recovers absolute 3D hands from one egocentric camera
EgoForce: Forearm-Guided Camera-Space 3D Hand Pose from a Monocular Egocentric Camera
-
Agentic search resolves external facts into pixel object locations
From Web to Pixels: Bringing Agentic Search into Visual Perception
-
Causal model generates coherent multi-shot videos in real time
CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narratives
-
Gaussian Splatting resolves its own photometric ambiguities
Revisiting Photometric Ambiguity for Accurate Gaussian-Splatting Surface Reconstruction
-
Self-reflective RL improves multimodal image generation and editing
AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward
-
Orthogonal transformations keep weight singular values fixed
Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformation
-
Coding agent memory hits 72.5% on long-term agent benchmark
LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleagues
-
Vision transformers scale linearly by routing patches through learned cores
Elastic Attention Cores for Scalable Vision Transformers
-
LLM refines embeddings at test time for up to 25% gains
Task-Adaptive Embedding Refinement via Test-time LLM Guidance
-
Fast-slow training triples sample efficiency for LLM adaptation
Learning, Fast and Slow: Towards LLMs That Adapt Continually
-
RL on bigger teachers then dense distillation beats direct GRPO on small students
Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training
-
ToolCUA reaches 46.85% accuracy by learning GUI-tool orchestration
ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents
-
Modality routing in RL improves audio-video generation
OmniNFT: Modality-wise Omni Diffusion Reinforcement for Joint Audio-Video Generation
-
LLM memory systems fail dependency reasoning across evolving entities
MEME: Multi-entity & Evolving Memory Evaluation
-
Routers align geometrically with experts they activate
Routers Learn the Geometry of Their Experts: Geometric Coupling in Sparse Mixture-of-Experts
-
Rubric RL checkpoints score higher on verifiers but lower on independent judges
Reward Hacking in Rubric-Based Reinforcement Learning
-
This paper derives an improved lower bound of order sqrt(n log log n) on the support size…
An Improved Lower Bound on Support Size of Capacity-Achieving Inputs for the Binomial Channel: Extended version
-
Pretrained transformers handle 128K contexts via KV-cache folding
KV-Fold: One-Step KV-Cache Recurrence for Long-Context Inference
-
Turnpike property stabilizes receding horizon games without terminals
Towards Closed-loop Stability of Nonlinear Receding Horizon Games
-
Attractor models beat larger transformers on language and puzzles
Solve the Loop: Attractor Models for Language and Reasoning
-
High-arity compression implies PAC learnability
High-arity Sample Compression
-
Block-scale search cuts quantization error 27% in BFP
Search Your Block Floating Point Scales!
-
Simulator trains AI agents on utility demand response
Towards Affordable Energy: A Gymnasium Environment for Electric Utility Demand-Response Programs
-
Sampler matches smooth-case rate for composite log-concave densities
A proximal gradient algorithm for composite log-concave sampling
-
Parallel streams let models read while writing
Multi-Stream LLMs: Unblocking Language Models with Parallel Streams of Thoughts, Inputs and Outputs
-
BFS width plus few backward arcs yields FPT for PAFP
Layer-Based Width for PAFP
-
Watermark detects AI text in mixed documents and distilled models
TextSeal: A Localized LLM Watermark for Provenance & Distillation Protection
-
Exact repair achieves optimal storage and bandwidth in quantum storage
Simultaneously Minimizing Storage and Bandwidth Under Exact Repair With Quantum Entanglement
-
Commercial 5G dataset aids AI handover and beam management
Enabling AI-Native Mobility in 6G: A Real-World Dataset for Handover, Beam Management, and Timing Advance
-
LLM political discourse lacks real population variation in crises
The Algorithmic Caricature: Auditing LLM-Generated Political Discourse Across Crisis Events
-
FuTCR improves new-class panoptic quality by up to 28%
FuTCR: Future-Targeted Contrast and Repulsion for Continual Panoptic Segmentation
-
Bivariate QSP gives optimal simulation of non-Hermitian Hamiltonians
Simulation of Non-Hermitian Hamiltonians with Bivariate Quantum Signal Processing
-
LychSim gives vision researchers Python control over Unreal scenes
LychSim: A Controllable and Interactive Simulation Framework for Vision Research