Search papers, labs, and topics across Lattice.
37 papers published across 4 labs.
LLMs can now understand and execute complex, semantic image edits from sparse drag inputs by inferring intended object-level transformations.
Reasoning supervision can be compressed over 450x with uncertainty-guided contraction, boosting LLM efficiency without sacrificing capability.
LVLMs can be trained to actively mentalize spatial scenes from novel viewpoints, boosting their reasoning accuracy by up to 20% on complex tasks.
Batching future MH proposals unlocks significant speedups for LLM power sampling without altering the core reasoning process.
Explicit 3D geometry, rendered as text, unlocks superior spatial reasoning in RGB-only VLMs by guiding trajectory correction during distillation.
LLMs can now understand and execute complex, semantic image edits from sparse drag inputs by inferring intended object-level transformations.
Reasoning supervision can be compressed over 450x with uncertainty-guided contraction, boosting LLM efficiency without sacrificing capability.
LVLMs can be trained to actively mentalize spatial scenes from novel viewpoints, boosting their reasoning accuracy by up to 20% on complex tasks.
Batching future MH proposals unlocks significant speedups for LLM power sampling without altering the core reasoning process.
Explicit 3D geometry, rendered as text, unlocks superior spatial reasoning in RGB-only VLMs by guiding trajectory correction during distillation.
Spatial coding agents can be distilled into standalone MLLMs, achieving superior spatial reasoning and generalization without external tools.
Even the best vision-language models struggle with predictive spatial reasoning, scoring less than 60% on a new benchmark designed to test anticipating unseen outcomes.
Visual transition reasoning, not just diverse data, unlocks significant multimodal LLM improvements, with just 2,000 examples boosting 22 benchmarks.
Looped Transformers can achieve tens of thousands of effective reasoning steps without performance collapse by learning to selectively retain and decay intermediate states.
Even state-of-the-art LMMs struggle with reasoning-informed visual editing, with the best model only achieving 56.6% accuracy on a new comprehensive benchmark.
City-scale audio-visual reasoning is currently dominated by expensive agentic pipelines, not standalone multimodal models.
Reasoning models can learn to plan by reverse-engineering solution ideas from hindsight, even when initially unable to solve the problem.
LLMs can now autonomously learn to self-improve at test-time, nearly doubling utility by intelligently selecting and applying TTT strategies.
Weisfeiler-Lehman graph kernels unlock superior structural features for algorithm selection, outperforming traditional methods on challenging constraint satisfaction problems.
Discarding just a few high-advantage rollouts during GRPO updates dramatically boosts LLM reasoning and exploration.
LLMs can attribute responsibility and blame, but their reasoning is incomplete and varies with model scale, with specific attribution dimensions demonstrably encoded in their latent spaces.
LLMs exhibit "Thinking Inertia," stubbornly continuing to show explicit reasoning even when explicitly instructed not to, particularly in open-ended tasks.
Agents can learn explicit, reusable mental models of partners to dramatically improve multi-agent interaction quality and Theory-of-Mind capabilities.
Action chunking unlocks temporally interpretable decision trees that match neural network performance with up to 80% fewer parameters.
Aggressively scaling exploration in RLVR without sacrificing model quality is now possible by distilling novel strategies from dedicated explorer policies.
LLM agents can now reliably track and fulfill complex deliverable requirements across numerous files without losing context, thanks to an environment-side "tab" that acts as a persistent, shared task ledger.
Fixed-weight Transformers can perfectly replicate iterative causal discovery algorithms, revealing a critical distinction between executing an algorithm and recovering the true causal structure.
An LLM-based agent achieves 18.3% out-of-sample returns in stock options trading by learning to select structured strategies, but surprisingly, retaining news during RL training halves performance.
Input-blind controls can account for substantial oracle headroom in adaptive computation, challenging the assumption that observed gains directly reflect the efficacy of selected layer programs.
Later Transformer layers in tabular foundation models aren't always the smartest; revisiting earlier thoughts dramatically boosts performance.
LLM capabilities diverge under latent sequence compression; language modeling, decodability, and reasoning do not share a single compression threshold.
The optimal strategy for the cow-path problem is provably cyclic, meaning no search algorithm can outperform a fixed path traversal order.
LLM-generated rules, not full trees, unlock efficient and interpretable few-shot tabular classification.
Machine learning agents discover new exact values for notoriously difficult-to-compute link invariants like slice genus and unknotting number.
Planning in visual world models can be accelerated by $5\times$ by pruning $50\%$ of spatial tokens based on their influence on the planning cost gradient, without sacrificing performance on most control tasks.
Long-horizon reasoning models can now achieve $O(1)$ memory and $O(N)$ time complexity while surpassing larger Transformer baselines on complex tasks.
Current LLMs struggle to translate visual scenes into executable geometric functions, failing even basic trajectory generation tasks.
AI agents can now build and reuse persistent, artifact-specific knowledge, dramatically improving their ability to find relevant information for complex tasks and reducing operational costs.
LLMs can learn to actively compute evidence by routing through retrieval and computation, dramatically improving performance on complex, multi-source reasoning tasks.
On-policy distillation excels at teaching LLMs to *use* their existing knowledge for complex reasoning, but doesn't actually teach them *new facts*.
English skeletons offer a minor, inconsistent boost in multilingual math reasoning, with optimal language choice proving highly context-dependent.
Sparse video reasoning can outperform dense observation models by learning to extract crucial temporal evidence from limited frames, even without explicit VQA annotations.
