AI & Machine Learning

S-VGGT introduces structure-aware subscene decomposition to break the quadratic scaling bottleneck of 3D foundation models.

Introduces a framework to generate complex, non-linear environments with mathematically guaranteed ground-truth optimal policies for RL benchmarking.

DSS-GAN is the first generative adversarial network to use a Mamba (State Space Model) backbone for high-quality image synthesis.

VectorWorld enables stable, real-time 1km+ closed-loop world model rollouts for autonomous driving using diffusion flow on vector graphs.

REAL achieves extreme quadruped parkour agility that is robust even to a 1-meter visual blind zone.

FINER discovers that MLLMs are highly prone to hallucination when images contain fine-grained mismatches co-occurring with real elements.

Synthetic videos of simple geometric shapes are more effective than massive real-world datasets for teaching video-language models fundamental temporal reasoning.

Lifting 2D features into a volumetric representation for robot manipulation policies yields a 14.8% success rate improvement by solving the 2D-3D spatial reasoning mismatch.

A new self-refining surrogate framework enables neural models to simulate complex dynamical systems over arbitrarily long horizons without the standard failure mode of compounding error.

Massive activation outliers in Transformers are an adaptive response to 'gradient sinks' during training, rather than just an inference-time quirk.

The 'consensus trap' in label-free RL—where models reinforce their own systematic errors—can be broken by co-evolving the model in alternating generator and verifier roles.

In-context memory for LLMs is fundamentally unreliable due to compaction loss and goal drift, but structured 'Knowledge Objects' provide a 252x cheaper and 100% accurate alternative.

Anomaly detection can be performed directly using a primary model's internal neuron output ranges, eliminating the need for expensive external AD models.

Truncated backpropagation for video decoding reduces the memory cost of fine-tuning video diffusion models from linear to constant.

Concept erasure in text-to-image models is largely a facade that can be bypassed using text-free inversion attacks.

LLMs compute and cache confidence scores automatically during answer generation, well before they are prompted to verbalize them.

ProbeFlow achieves 14.8x faster action decoding in Vision-Language-Action (VLA) models without any retraining.

DebugLM allows developers to trace an LLM's specific behaviors back to individual training data sources.

Measuring the distance between human languages can now be done quantitatively using the attention mechanisms of multilingual transformers.

Large Language Models can maintain performance with only 16-64 unique weight values per matrix, as only the relative rank of weights matters.

Parallel multi-token prediction can be achieved in standard LLMs without training auxiliary models or modifying weights.

CARE provides a recipe for converting standard GQA models into high-efficiency Multi-head Latent Attention (MLA) architectures.

VideoAtlas enables navigation and reasoning over long-form video using compute that scales only logarithmically with video length.

Enforce formal safety and Signal Temporal Logic (STL) constraints on robotics foundation models without retraining.

MUD provides a faster, lower-overhead alternative to Muon for transformer training, achieving up to 2.6x higher throughput.

LoST introduces a semantic-first 3D tokenizer that reduces the token count for 3D shape generation by up to 99.9%.

AgentFactory shifts agent evolution from unreliable textual 'reflections' to a library of verifiable, executable Python subagents.

SkeletonLLM allows frozen Multimodal LLMs to reason about human motion by rendering skeleton sequences into their native visual modality.

DAPS++ reinterprets diffusion inverse problems as a decoupled EM-style initialization, significantly increasing restoration speed and stability.

Motion-MLLM integrates IMU egomotion data into Video-LLMs to solve the fundamental scale and spatial reasoning ambiguities of purely visual models.

Provides the first theoretical proof that Graph Transformers structurally prevent the 'oversmoothing' failure mode inherent to deep GCNs.

Imagine an AI virus that doesn't just sit there—it copies itself and jumps from one AI to the next all on its own.

A new VR headset uses mirrors to kill the lag that makes you want to puke.

These tiny sliding antennas are hacking the laws of physics to give you a perfect signal where your phone usually dies.

New AI can peer into a computer chip's microscopic guts to find "spy tech" hidden by sketchy manufacturers.

Researchers built a "ghost mode" for robots that calculates the exact path to sneak around without being seen.

Turns out the long lines at airport security were secretly keeping the whole U.S. flight network from crashing for the last decade.

RSM achieves 20x faster training for recursive reasoning models and enables test-time scaling for up to 20,000 refinement steps.

A factorial study on EHR foundation models reveals that joint encoding of code-attribute pairs (local binding) is the primary driver of performance and efficiency.

Alternating Reinforcement Learning with Rubric Rewards (ARL-RR) replaces brittle scalar reward aggregation with a semantic meta-class optimization framework.

Self-reflective program search matches or outperforms recursive language models for long-context tasks, suggesting recursion itself is not the primary driver of performance.

Dynamic Representational Circuit Breaking (DRCB) introduces an architectural defense against steganographic collusion in multi-agent RL by monitoring and shuffling latent communication bottlenecks.

Theoretical and empirical evidence suggests that the 'Key' mechanism in Attention may be redundant, proposing a 'QV' paradigm that simplifies Transformer architectures.

Atlas introduces 'Compiled Memory,' which rewrites an agent's system prompt with distilled task experience rather than using RAG or fine-tuning.

Latent Posterior Factors (LPF) bridge neural representations with structured probabilistic reasoning by converting VAE posteriors into factors for Sum-Product Networks.

Spectral Edge Dynamics (SED) provides an early-warning signal for grokking, predicting generalization up to 1,700 steps before it occurs.

Transition Flow Matching learns a global transition flow rather than local velocity fields, enabling single-step generation and transfer to arbitrary future time points.

Robot policy performance can be improved by up to 60% by identifying a single 'golden ticket' constant noise vector instead of sampling from a Gaussian.

Simulation Distillation (SimDist) enables rapid sim-to-real adaptation by transferring reward and value models directly into a latent world model.

Demonstrates that massive scaling of diverse simulator resets can replace manual curriculum engineering for complex dexterous manipulation.